[Issue]: Naming error when trying to install and run Flux qint4

Issue Description

When trying to install Flux qint4 I get the error below, then it installs both Flux dev and Flux qint4 and reverts to Flux dev when attempting to generate T2I

08:28:42-532859 ERROR Loading FLUX: Failed to load Quanto transformer: Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is 96: 'Diffusers\Disty0/FLUX.1-dev-qint4'.

This is what it installs in the diffusers folder

Flux dev is unusable due to high VRAM consumption but this is known already.

Full log (model installation + attempting T2I) below

Version Platform Description

08:22:55-184036 INFO Python version=3.11.9 platform=Windows bin="C:\ai\automatic\venv\Scripts\python.exe" venv="C:\ai\automatic\venv" 08:22:55-378508 INFO Version: app=sd.next updated=2024-09-02 hash=bba17766 branch=dev url=https://github.com/vladmandic/automatic/tree/dev ui=dev 08:22:56-191172 INFO Latest published version: bab17a0b4f91b41c885f10262ef8c8e70ba72faa 2024-08-31T20:57:34Z 08:22:56-204169 INFO Platform: arch=AMD64 cpu=Intel64 Family 6 Model 165 Stepping 5, GenuineIntel system=Windows release=Windows-10-10.0.22631-SP0 python=3.11.9

Relevant log output

PS C:\ai\automatic> .\webui.bat --medvram --debug
Using VENV: C:\ai\automatic\venv
08:22:55-179048 INFO     Starting SD.Next
08:22:55-182040 INFO     Logger: file="C:\ai\automatic\sdnext.log" level=DEBUG size=65 mode=create
08:22:55-184036 INFO     Python version=3.11.9 platform=Windows bin="C:\ai\automatic\venv\Scripts\python.exe"
                         venv="C:\ai\automatic\venv"
08:22:55-378508 INFO     Version: app=sd.next updated=2024-09-02 hash=bba17766 branch=dev
                         url=https://github.com/vladmandic/automatic/tree/dev ui=dev
08:22:56-191172 INFO     Latest published version: bab17a0b4f91b41c885f10262ef8c8e70ba72faa 2024-08-31T20:57:34Z
08:22:56-204169 INFO     Platform: arch=AMD64 cpu=Intel64 Family 6 Model 165 Stepping 5, GenuineIntel system=Windows
                         release=Windows-10-10.0.22631-SP0 python=3.11.9
08:22:56-206160 DEBUG    Setting environment tuning
08:22:56-207130 INFO     HF cache folder: C:\Users\sebas\.cache\huggingface\hub
08:22:56-209125 DEBUG    Torch allocator: "garbage_collection_threshold:0.80,max_split_size_mb:512"
08:22:56-219929 DEBUG    Torch overrides: cuda=False rocm=False ipex=False diml=False openvino=False
08:22:56-221134 DEBUG    Torch allowed: cuda=True rocm=True ipex=True diml=True openvino=True
08:22:56-232221 INFO     nVidia CUDA toolkit detected: nvidia-smi present
08:22:56-313452 WARNING  Modified files: ['models/Reference/playgroundai--playground-v2-1024px-aesthetic.jpg']
08:22:56-403214 INFO     Verifying requirements
08:22:56-407228 INFO     Verifying packages
08:22:56-450259 DEBUG    Repository update time: Tue Sep  3 01:08:32 2024
08:22:56-450821 INFO     Startup: standard
08:22:56-452117 INFO     Verifying submodules
08:22:59-888555 DEBUG    Git detached head detected: folder="extensions-builtin/sd-extension-chainner" reattach=main
08:22:59-889846 DEBUG    Submodule: extensions-builtin/sd-extension-chainner / main
08:23:00-009633 DEBUG    Git detached head detected: folder="extensions-builtin/sd-extension-system-info" reattach=main
08:23:00-011627 DEBUG    Submodule: extensions-builtin/sd-extension-system-info / main
08:23:00-132141 DEBUG    Git detached head detected: folder="extensions-builtin/sd-webui-agent-scheduler" reattach=main
08:23:00-133139 DEBUG    Submodule: extensions-builtin/sd-webui-agent-scheduler / main
08:23:00-301094 DEBUG    Git detached head detected: folder="extensions-builtin/sdnext-modernui" reattach=dev
08:23:00-302121 DEBUG    Submodule: extensions-builtin/sdnext-modernui / dev
08:23:00-444978 DEBUG    Git detached head detected: folder="extensions-builtin/stable-diffusion-webui-rembg"
                         reattach=master
08:23:00-445976 DEBUG    Submodule: extensions-builtin/stable-diffusion-webui-rembg / master
08:23:00-567390 DEBUG    Git detached head detected: folder="modules/k-diffusion" reattach=master
08:23:00-568388 DEBUG    Submodule: modules/k-diffusion / master
08:23:00-686117 DEBUG    Git detached head detected: folder="wiki" reattach=master
08:23:00-687142 DEBUG    Submodule: wiki / master
08:23:00-759576 DEBUG    Register paths
08:23:00-846371 DEBUG    Installed packages: 207
08:23:00-847608 DEBUG    Extensions all: ['Lora', 'sd-extension-chainner', 'sd-extension-system-info',
                         'sd-webui-agent-scheduler', 'sd-webui-controlnet', 'sdnext-modernui',
                         'stable-diffusion-webui-images-browser', 'stable-diffusion-webui-rembg']
08:23:01-025059 DEBUG    Running extension installer:
                         C:\ai\automatic\extensions-builtin\sd-extension-system-info\install.py
08:23:01-393054 DEBUG    Running extension installer:
                         C:\ai\automatic\extensions-builtin\sd-webui-agent-scheduler\install.py
08:23:01-757647 DEBUG    Running extension installer: C:\ai\automatic\extensions-builtin\sd-webui-controlnet\install.py
08:23:02-266898 DEBUG    Running extension installer:
                         C:\ai\automatic\extensions-builtin\stable-diffusion-webui-images-browser\install.py
08:23:02-632486 DEBUG    Running extension installer:
                         C:\ai\automatic\extensions-builtin\stable-diffusion-webui-rembg\install.py
08:23:02-996279 DEBUG    Extensions all: []
08:23:02-997230 INFO     Extensions enabled: ['Lora', 'sd-extension-chainner', 'sd-extension-system-info',
                         'sd-webui-agent-scheduler', 'sd-webui-controlnet', 'sdnext-modernui',
                         'stable-diffusion-webui-images-browser', 'stable-diffusion-webui-rembg']
08:23:02-999228 INFO     Verifying requirements
08:23:03-000225 DEBUG    Setup complete without errors: 1725340983
08:23:03-006918 DEBUG    Extension preload: {'extensions-builtin': 0.0, 'extensions': 0.0}
08:23:03-007886 DEBUG    Starting module: <module 'webui' from 'C:\\ai\\automatic\\webui.py'>
08:23:03-008883 INFO     Command line args: ['--medvram', '--debug'] medvram=True debug=True
08:23:03-009881 DEBUG    Env flags: []
08:23:08-808284 INFO     Load packages: {'torch': '2.4.0+cu124', 'diffusers': '0.31.0.dev0', 'gradio': '3.43.2'}
08:23:09-836090 DEBUG    Read: file="config.json" json=35 bytes=1455 time=0.000
08:23:09-838085 DEBUG    Unknown settings: ['cross_attention_options']
08:23:09-840080 INFO     Engine: backend=Backend.DIFFUSERS compute=cuda device=cuda attention="Scaled-Dot-Product"
                         mode=no_grad
08:23:09-898922 INFO     Device: device=NVIDIA GeForce RTX 4080 n=1 arch=sm_90 cap=(8, 9) cuda=12.4 cudnn=90100
                         driver=560.81
08:23:09-900917 DEBUG    Read: file="html\reference.json" json=52 bytes=29118 time=0.001
08:23:10-300475 DEBUG    ONNX: version=1.19.0 provider=CUDAExecutionProvider, available=['AzureExecutionProvider',
                         'CPUExecutionProvider']
08:23:10-478064 DEBUG    Importing LDM
08:23:10-493584 DEBUG    Entering start sequence
08:23:10-496353 DEBUG    Initializing
08:23:10-521259 INFO     Available VAEs: path="models\VAE" items=0
08:23:10-523255 DEBUG    Available UNets: path="models\UNET" items=0
08:23:10-524901 DEBUG    Available T5s: path="models\T5" items=0
08:23:10-525871 INFO     Disabled extensions: ['sd-webui-controlnet', 'sdnext-modernui']
08:23:10-527865 DEBUG    Read: file="cache.json" json=2 bytes=10089 time=0.000
08:23:10-534874 DEBUG    Read: file="metadata.json" json=470 bytes=1620174 time=0.005
08:23:10-539834 DEBUG    Scanning diffusers cache: folder=models\Diffusers items=0 time=0.00
08:23:10-541198 INFO     Available models: path="models\Stable-diffusion" items=20 time=0.01
08:23:10-730721 DEBUG    Load extensions
08:23:10-778022 INFO     Extension: script='extensions-builtin\Lora\scripts\lora_script.py'
                         [2;36m08:23:10-775030[0m[2;36m [0m[34mINFO    [0m LoRA networks: [33mavailable[0m=[1;36m70[0m
                         [33mfolders[0m=[1;36m2[0m
08:23:11-151765 INFO     Extension: script='extensions-builtin\sd-webui-agent-scheduler\scripts\task_scheduler.py' Using
                         sqlite file: extensions-builtin\sd-webui-agent-scheduler\task_scheduler.sqlite3
08:23:11-346834 DEBUG    Extensions init time: 0.61 sd-webui-agent-scheduler=0.33
                         stable-diffusion-webui-images-browser=0.18
08:23:11-359800 DEBUG    Read: file="html/upscalers.json" json=4 bytes=2672 time=0.000
08:23:11-360797 DEBUG    Read: file="extensions-builtin\sd-extension-chainner\models.json" json=24 bytes=2719 time=0.000
08:23:11-362792 DEBUG    chaiNNer models: path="models\chaiNNer" defined=24 discovered=0 downloaded=8
08:23:11-364786 DEBUG    Upscaler type=ESRGAN folder="models\ESRGAN" model="1x-ITF-SkinDiffDetail-Lite-v1"
                         path="models\ESRGAN\1x-ITF-SkinDiffDetail-Lite-v1.pth"
08:23:11-365783 DEBUG    Upscaler type=ESRGAN folder="models\ESRGAN" model="4xNMKDSuperscale_4xNMKDSuperscale"
                         path="models\ESRGAN\4xNMKDSuperscale_4xNMKDSuperscale.pth"
08:23:11-366781 DEBUG    Upscaler type=ESRGAN folder="models\ESRGAN" model="4x_NMKD-Siax_200k"
                         path="models\ESRGAN\4x_NMKD-Siax_200k.pth"
08:23:11-369772 DEBUG    Load upscalers: total=56 downloaded=11 user=3 time=0.02 ['None', 'Lanczos', 'Nearest',
                         'ChaiNNer', 'AuraSR', 'ESRGAN', 'LDSR', 'RealESRGAN', 'SCUNet', 'SD', 'SwinIR']
08:23:11-386728 DEBUG    Load styles: folder="models\styles" items=288 time=0.01
08:23:11-389720 DEBUG    Creating UI
08:23:11-390717 DEBUG    UI themes available: type=Standard themes=12
08:23:11-391893 INFO     UI theme: type=Standard name="black-teal"
08:23:11-399489 DEBUG    UI theme: css="C:\ai\automatic\javascript\black-teal.css" base="sdnext.css" user="None"
08:23:11-401485 DEBUG    UI initialize: txt2img
08:23:11-460851 DEBUG    Networks: page='model' items=71 subfolders=2 tab=txt2img folders=['models\\Stable-diffusion',
                         'models\\Diffusers', 'models\\Reference'] list=0.04 thumb=0.00 desc=0.01 info=0.00 workers=4
                         sort=Default
08:23:11-469245 DEBUG    Networks: page='lora' items=70 subfolders=0 tab=txt2img folders=['models\\Lora',
                         'models\\LyCORIS'] list=0.04 thumb=0.01 desc=0.02 info=0.02 workers=4 sort=Default
08:23:11-500190 DEBUG    Networks: page='style' items=288 subfolders=1 tab=txt2img folders=['models\\styles', 'html']
                         list=0.04 thumb=0.00 desc=0.00 info=0.00 workers=4 sort=Default
08:23:11-505597 DEBUG    Networks: page='embedding' items=13 subfolders=0 tab=txt2img folders=['models\\embeddings']
                         list=0.03 thumb=0.01 desc=0.00 info=0.00 workers=4 sort=Default
08:23:11-507560 DEBUG    Networks: page='vae' items=0 subfolders=0 tab=txt2img folders=['models\\VAE'] list=0.00
                         thumb=0.00 desc=0.00 info=0.00 workers=4 sort=Default
08:23:11-581390 DEBUG    UI initialize: img2img
08:23:11-822779 DEBUG    UI initialize: control models=models\control
08:23:12-077976 DEBUG    Read: file="ui-config.json" json=0 bytes=2 time=0.000
08:23:12-178414 DEBUG    UI themes available: type=Standard themes=12
08:23:12-704712 DEBUG    Reading failed: C:\ai\automatic\html\extensions.json [Errno 2] No such file or directory:
                         'C:\\ai\\automatic\\html\\extensions.json'
08:23:12-705738 INFO     Extension list is empty: refresh required
08:23:13-287174 DEBUG    Extension list: processed=8 installed=8 enabled=6 disabled=2 visible=8 hidden=0
08:23:13-614300 DEBUG    Root paths: ['C:\\ai\\automatic']
08:23:13-690228 INFO     Local URL: http://127.0.0.1:7860/
08:23:13-691226 DEBUG    Gradio functions: registered=2361
08:23:13-692376 DEBUG    FastAPI middleware: ['Middleware', 'Middleware']
08:23:13-695397 DEBUG    Creating API
08:23:13-861417 INFO     [AgentScheduler] Task queue is empty
08:23:13-862105 INFO     [AgentScheduler] Registering APIs
08:23:13-980818 DEBUG    Scripts setup: ['IP Adapters:0.023', 'AnimateDiff:0.008', 'X/Y/Z Grid:0.011', 'Face:0.01']
08:23:13-982092 DEBUG    Model metadata: file="metadata.json" no changes
08:23:13-983377 DEBUG    Torch mode: deterministic=False
08:23:14-011305 INFO     Torch override VAE dtype: no-half set
08:23:14-012019 DEBUG    Desired Torch parameters: dtype=FP16 no-half=False no-half-vae=True upscast=False
08:23:14-013044 INFO     Setting Torch parameters: device=cuda dtype=torch.float16 vae=torch.float32 unet=torch.float16
                         context=no_grad fp16=True bf16=None optimization=Scaled-Dot-Product
08:23:14-015013 DEBUG    Model requested: fn=<lambda>
08:23:14-016011 WARNING  Selected: model="Diffusers\Disty0/FLUX.1-dev-qint4 [82811df42b]" not found
08:23:14-017764 DEBUG    Script callback init time: image_browser.py:ui_tabs=0.39 system-info.py:app_started=0.06
                         task_scheduler.py:app_started=0.13
08:23:14-018792 INFO     Startup time: 11.01 torch=4.11 gradio=1.27 diffusers=0.41 libraries=1.67 extensions=0.61
                         face-restore=0.19 ui-en=0.21 ui-txt2img=0.05 ui-img2img=0.21 ui-control=0.11 ui-settings=0.23
                         ui-extensions=1.02 ui-defaults=0.25 launch=0.13 api=0.09 app-started=0.20
08:23:14-020790 DEBUG    Save: file="config.json" json=35 bytes=1408 time=0.003
08:23:14-022783 DEBUG    Unused settings: ['cross_attention_options']
08:24:00-035737 DEBUG    Server: alive=True jobs=1 requests=1 uptime=51 memory=0.98/63.92 backend=Backend.DIFFUSERS
                         state=idle
08:26:00-077613 DEBUG    Server: alive=True jobs=1 requests=1 uptime=171 memory=0.98/63.92 backend=Backend.DIFFUSERS
                         state=idle
08:26:28-669831 INFO     MOTD: N/A
08:26:31-238331 DEBUG    UI themes available: type=Standard themes=12
08:26:31-427893 INFO     Browser session: user=None client=127.0.0.1 agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64)
                         AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36 Edg/128.0.0.0
08:26:46-170132 DEBUG    Reference: download="Disty0/FLUX.1-dev-qint4"
08:26:46-172164 DEBUG    Diffusers downloading: id="Disty0/FLUX.1-dev-qint4" args={'force_download': False,
                         'resume_download': True, 'cache_dir': 'models\\Diffusers', 'load_connected_pipeline': True}
model_index.json: 100%|███████████████████████████████████████████████████████████████████████| 536/536 [00:00<?, ?B/s]
text_encoder/config.json: 100%|███████████████████████████████████████████████████████████████| 613/613 [00:00<?, ?B/s]
scheduler/scheduler_config.json: 100%|████████████████████████████████████████████████████████| 273/273 [00:00<?, ?B/s]
text_encoder_2/config.json: 100%|█████████████████████████████████████████████████████████████| 909/909 [00:00<?, ?B/s]
tokenizer/tokenizer_config.json: 100%|████████████████████████████████████████████████████████| 705/705 [00:00<?, ?B/s]
tokenizer_2/special_tokens_map.json: 100%|████████████████████████████████████████████████| 2.54k/2.54k [00:00<?, ?B/s]
tokenizer/special_tokens_map.json: 100%|██████████████████████████████████████████████████████| 588/588 [00:00<?, ?B/s]
transformer/config.json: 100%|████████████████████████████████████████████████████████████████| 535/535 [00:00<?, ?B/s]
tokenizer_2/tokenizer_config.json: 100%|██████████████████████████████████████████████████| 20.8k/20.8k [00:00<?, ?B/s]
spiece.model: 100%|█████████████████████████████████████████████████████████████████| 792k/792k [00:00<00:00, 10.5MB/s]
tokenizer/merges.txt: 100%|█████████████████████████████████████████████████████████| 525k/525k [00:00<00:00, 1.23MB/s]
tokenizer/vocab.json: 100%|███████████████████████████████████████████████████████| 1.06M/1.06M [00:00<00:00, 1.99MB/s]
vae/config.json: 100%|████████████████████████████████████████████████████████████████████████| 820/820 [00:00<?, ?B/s]
tokenizer_2/tokenizer.json: 100%|█████████████████████████████████████████████████| 2.42M/2.42M [00:00<00:00, 3.14MB/s]
diffusion_pytorch_model.safetensors: 100%|██████████████████████████████████████████| 168M/168M [00:05<00:00, 33.0MB/s]
model.safetensors: 100%|████████████████████████████████████████████████████████████| 246M/246M [00:08<00:00, 29.7MB/s]
model.safetensors: 100%|██████████████████████████████████████████████████████████| 2.72G/2.72G [00:49<00:00, 54.9MB/s]
Fetching 18 files:  33%|█████████████████████▎                                          | 6/18 [00:50<02:11, 10.95s/it]08:28:00-206307 DEBUG    Server: alive=True jobs=2 requests=71 uptime=291 memory=1.01/63.92 backend=Backend.DIFFUSERS
                         state=job="HuggingFace" 0/-1
diffusion_pytorch_model.safetensors: 100%|████████████████████████████████████████| 6.33G/6.33G [01:47<00:00, 58.8MB/s]
Fetching 18 files: 100%|███████████████████████████████████████████████████████████████| 18/18 [01:49<00:00,  6.09s/it]
08:28:36-991476 DEBUG    Save:
                         file="models\Diffusers\models--Disty0--FLUX.1-dev-qint4\snapshots\82811df42b556a1153b971d8375d5
                         170c306a6eb\model_info.json" json=12 bytes=214 time=0.001
08:28:36-993470 DEBUG    Reference download complete: model="Disty0/FLUX.1-dev-qint4"
08:28:36-998455 DEBUG    Scanning diffusers cache: folder=models\Diffusers items=1 time=0.00
08:28:37-000452 INFO     Available models: path="models\Stable-diffusion" items=21 time=0.01
08:28:37-481165 INFO     Select: model="Diffusers\Disty0/FLUX.1-dev-qint4 [82811df42b]"
08:28:37-483160 DEBUG    Load model: existing=False
                         target=models\Diffusers\models--Disty0--FLUX.1-dev-qint4\snapshots\82811df42b556a1153b971d8375d
                         5170c306a6eb info=None
08:28:37-485182 DEBUG    Diffusers loading:
                         path="models\Diffusers\models--Disty0--FLUX.1-dev-qint4\snapshots\82811df42b556a1153b971d8375d5
                         170c306a6eb"
08:28:37-486152 INFO     Autodetect: model="FLUX" class=FluxPipeline
                         file="models\Diffusers\models--Disty0--FLUX.1-dev-qint4\snapshots\82811df42b556a1153b971d8375d5
                         170c306a6eb" size=0MB
08:28:37-504103 DEBUG    Loading FLUX: model="Diffusers\Disty0/FLUX.1-dev-qint4" unet="None" t5="None" vae="None"
                         quant=qint4 offload=model dtype=torch.float16
08:28:37-505100 INFO     Install: package="optimum-quanto" mode=pip
08:28:37-506099 DEBUG    Running: pip="install --upgrade optimum-quanto"
08:28:42-532859 ERROR    Loading FLUX: Failed to load Quanto transformer: Repo id must use alphanumeric chars or '-',
                         '_', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is
                         96: 'Diffusers\Disty0/FLUX.1-dev-qint4'.
08:28:42-533856 ERROR    FLUX Quanto:: HFValidationError
╭───────────────────────────────────────── Traceback (most recent call last) ──────────────────────────────────────────╮
│ C:\ai\automatic\modules\model_flux.py:50 in load_flux_quanto                                                         │
│                                                                                                                      │
│    49 │   │   │   repo_id = checkpoint_info.name.replace('Diffusers/', '')                                           │
│ ❱  50 │   │   │   quantization_map = hf_hub_download(repo_id, subfolder='transformer', filename='quantization_map.js │
│    51 │   │   with open(quantization_map, "r", encoding='utf8') as f:                                                │
│                                                                                                                      │
│ C:\ai\automatic\venv\Lib\site-packages\huggingface_hub\utils\_deprecation.py:101 in inner_f                          │
│                                                                                                                      │
│   100 │   │   │   │   warnings.warn(message, FutureWarning)                                                          │
│ ❱ 101 │   │   │   return f(*args, **kwargs)                                                                          │
│   102                                                                                                                │
│                                                                                                                      │
│ C:\ai\automatic\venv\Lib\site-packages\huggingface_hub\utils\_validators.py:106 in _inner_fn                         │
│                                                                                                                      │
│   105 │   │   │   if arg_name in ["repo_id", "from_id", "to_id"]:                                                    │
│ ❱ 106 │   │   │   │   validate_repo_id(arg_value)                                                                    │
│   107                                                                                                                │
│                                                                                                                      │
│ C:\ai\automatic\venv\Lib\site-packages\huggingface_hub\utils\_validators.py:160 in validate_repo_id                  │
│                                                                                                                      │
│   159 │   if not REPO_ID_REGEX.match(repo_id):                                                                       │
│ ❱ 160 │   │   raise HFValidationError(                                                                               │
│   161 │   │   │   "Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are"                          │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
HFValidationError: Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is 96: 'Diffusers\Disty0/FLUX.1-dev-qint4'.
08:28:42-581912 ERROR    Loading FLUX: Failed to load Quanto text encoder: Repo id must use alphanumeric chars or '-',
                         '_', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is
                         96: 'Diffusers\Disty0/FLUX.1-dev-qint4'.
08:28:42-583450 ERROR    FLUX Quanto:: HFValidationError
╭───────────────────────────────────────── Traceback (most recent call last) ──────────────────────────────────────────╮
│ C:\ai\automatic\modules\model_flux.py:74 in load_flux_quanto                                                         │
│                                                                                                                      │
│    73 │   │   │   repo_id = checkpoint_info.name.replace('Diffusers/', '')                                           │
│ ❱  74 │   │   │   quantization_map = hf_hub_download(repo_id, subfolder='text_encoder_2', filename='quantization_map │
│    75 │   │   with open(quantization_map, "r", encoding='utf8') as f:                                                │
│                                                                                                                      │
│ C:\ai\automatic\venv\Lib\site-packages\huggingface_hub\utils\_deprecation.py:101 in inner_f                          │
│                                                                                                                      │
│   100 │   │   │   │   warnings.warn(message, FutureWarning)                                                          │
│ ❱ 101 │   │   │   return f(*args, **kwargs)                                                                          │
│   102                                                                                                                │
│                                                                                                                      │
│ C:\ai\automatic\venv\Lib\site-packages\huggingface_hub\utils\_validators.py:106 in _inner_fn                         │
│                                                                                                                      │
│   105 │   │   │   if arg_name in ["repo_id", "from_id", "to_id"]:                                                    │
│ ❱ 106 │   │   │   │   validate_repo_id(arg_value)                                                                    │
│   107                                                                                                                │
│                                                                                                                      │
│ C:\ai\automatic\venv\Lib\site-packages\huggingface_hub\utils\_validators.py:160 in validate_repo_id                  │
│                                                                                                                      │
│   159 │   if not REPO_ID_REGEX.match(repo_id):                                                                       │
│ ❱ 160 │   │   raise HFValidationError(                                                                               │
│   161 │   │   │   "Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are"                          │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
HFValidationError: Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is 96: 'Diffusers\Disty0/FLUX.1-dev-qint4'.
08:28:42-606031 DEBUG    Loading FLUX: preloaded=[]
model_index.json: 100%|████████████████████████████████████████████████████████████████| 536/536 [00:00<00:00, 537kB/s]
text_encoder/config.json: 100%|███████████████████████████████████████████████████████████████| 613/613 [00:00<?, ?B/s]
(…)t_encoder_2/model.safetensors.index.json: 100%|████████████████████████████████| 19.9k/19.9k [00:00<00:00, 19.9MB/s]
scheduler/scheduler_config.json: 100%|████████████████████████████████████████████████████████| 273/273 [00:00<?, ?B/s]
tokenizer/special_tokens_map.json: 100%|██████████████████████████████████████████████████████| 588/588 [00:00<?, ?B/s]
tokenizer/tokenizer_config.json: 100%|████████████████████████████████████████████████████████| 705/705 [00:00<?, ?B/s]
text_encoder_2/config.json: 100%|██████████████████████████████████████████████████████| 782/782 [00:00<00:00, 783kB/s]
tokenizer_2/special_tokens_map.json: 100%|████████████████████████████████████████████████| 2.54k/2.54k [00:00<?, ?B/s]
tokenizer/merges.txt: 100%|█████████████████████████████████████████████████████████| 525k/525k [00:00<00:00, 1.28MB/s]
tokenizer/vocab.json: 100%|███████████████████████████████████████████████████████| 1.06M/1.06M [00:00<00:00, 2.72MB/s]
spiece.model: 100%|█████████████████████████████████████████████████████████████████| 792k/792k [00:00<00:00, 15.6MB/s]
tokenizer_2/tokenizer_config.json: 100%|██████████████████████████████████████████████████| 20.8k/20.8k [00:00<?, ?B/s]
transformer/config.json: 100%|████████████████████████████████████████████████████████████████| 378/378 [00:00<?, ?B/s]
(…)ion_pytorch_model.safetensors.index.json: 100%|███████████████████████████████████| 121k/121k [00:00<00:00, 868kB/s]
tokenizer_2/tokenizer.json: 100%|█████████████████████████████████████████████████| 2.42M/2.42M [00:00<00:00, 3.32MB/s]
vae/config.json: 100%|████████████████████████████████████████████████████████████████████████| 820/820 [00:00<?, ?B/s]
diffusion_pytorch_model.safetensors: 100%|██████████████████████████████████████████| 168M/168M [00:10<00:00, 16.1MB/s]
model.safetensors: 100%|████████████████████████████████████████████████████████████| 246M/246M [00:14<00:00, 16.5MB/s]
Fetching 23 files:  17%|███████████▏                                                    | 4/23 [00:17<01:34,  4.96s/it]08:29:59-948363 DEBUG    Server: alive=True jobs=2 requests=84 uptime=411 memory=1.09/63.92 backend=Backend.DIFFUSERS
                         state=idle
model-00001-of-00002.safetensors:   5%|██▍                                         | 273M/4.99G [00:14<03:58, 19.8MB/s]08:31:59-987827 DEBUG    Server: alive=True jobs=2 requests=90 uptime=531 memory=1.08/63.92 backend=Backend.DIFFUSERS
                         state=idle
(…)pytorch_model-00003-of-00003.safetensors: 100%|████████████████████████████████| 3.87G/3.87G [04:41<00:00, 13.8MB/s]
model-00002-of-00002.safetensors: 100%|███████████████████████████████████████████| 4.53G/4.53G [04:48<00:00, 15.7MB/s]
model-00001-of-00002.safetensors: 100%|███████████████████████████████████████████| 4.99G/4.99G [05:03<00:00, 16.5MB/s]
Fetching 23 files:  26%|████████████████▋                                               | 6/23 [05:06<19:28, 68.75s/it]08:34:00-025220 DEBUG    Server: alive=True jobs=2 requests=107 uptime=651 memory=1.04/63.92 backend=Backend.DIFFUSERS
                         state=idle
model-00001-of-00002.safetensors: 100%|██████████████████████████████████████████▉| 4.99G/4.99G [05:03<00:00, 46.4MB/s]08:35:59-973116 DEBUG    Server: alive=True jobs=2 requests=113 uptime=771 memory=1.04/63.92 backend=Backend.DIFFUSERS
                         state=idle
(…)pytorch_model-00002-of-00003.safetensors: 100%|████████████████████████████████| 9.95G/9.95G [07:49<00:00, 21.2MB/s]
(…)pytorch_model-00001-of-00003.safetensors: 100%|████████████████████████████████| 9.98G/9.98G [07:53<00:00, 21.1MB/s]
Fetching 23 files: 100%|███████████████████████████████████████████████████████████████| 23/23 [07:55<00:00, 20.69s/it]

Loading checkpoint shards:   0%|                                                                 | 0/2 [00:00<?, ?it/s]
[A

Loading checkpoint shards:  50%|############################5                            | 1/2 [00:04<00:04,  4.77s/it]
[A

Loading checkpoint shards: 100%|#########################################################| 2/2 [00:09<00:00,  4.49s/it]
[A
Loading checkpoint shards: 100%|#########################################################| 2/2 [00:09<00:00,  4.54s/it]

Loading pipeline components... 100% ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 7/7  [ 0:01:02 < 0:00:00 , 2 C/s ]
08:37:41-431087 INFO     Load embeddings: loaded=0 skipped=13 time=0.04
08:37:41-506912 DEBUG    Setting model VAE: no-half=True
08:37:41-508610 DEBUG    Setting model: slicing=True
08:37:41-509234 DEBUG    Setting model: tiling=True
08:37:41-510233 DEBUG    Setting model: attention=Scaled-Dot-Product
08:37:41-535529 DEBUG    Setting model: offload=model
08:37:41-773417 DEBUG    GC: utilization={'gpu': 8, 'ram': 54, 'threshold': 80} gc={'collected': 304, 'saved': 0.0}
                         before={'gpu': 1.33, 'ram': 34.57} after={'gpu': 1.33, 'ram': 34.57, 'retries': 0, 'oom': 0}
                         device=cuda fn=load_diffuser time=0.21
08:37:41-775316 INFO     Load model: time=544.08 load=543.90 options=0.10 native=1024 {'ram': {'used': 34.57, 'total':
                         63.92}, 'gpu': {'used': 1.33, 'total': 15.99}, 'retries': 0, 'oom': 0}
08:37:41-777591 DEBUG    Setting changed: sd_model_checkpoint=Disty0/FLUX.1-dev-qint4 progress=True
08:37:41-780607 DEBUG    Save: file="config.json" json=35 bytes=1408 time=0.003
08:37:41-781582 DEBUG    Unused settings: ['cross_attention_options']
08:38:00-051702 DEBUG    Server: alive=True jobs=2 requests=121 uptime=891 memory=34.57/63.92 backend=Backend.DIFFUSERS
                         state=idle
08:39:05-621128 INFO     Base: class=FluxPipeline
08:39:05-624120 DEBUG    Sampler default FlowMatchEulerDiscreteScheduler: {'num_train_timesteps': 1000, 'shift': 3.0,
                         'use_dynamic_shifting': True, 'base_shift': 0.5, 'max_shift': 1.15, 'base_image_seq_len': 256,
                         'max_image_seq_len': 4096}
08:39:05-656036 DEBUG    Torch generator: device=cuda seeds=[3163949593]
08:39:05-657033 DEBUG    Diffuser pipeline: FluxPipeline task=DiffusersTaskType.TEXT_2_IMAGE batch=1/1x1 set={'prompt':
                         1, 'guidance_scale': 6, 'num_inference_steps': 20, 'output_type': 'latent', 'width': 1024,
                         'height': 1024, 'parser': 'Fixed attention'}
Progress ?it/s                                              0% 0/20 00:00 ? Base

Backend

Diffusers

UI

Standard

Branch

Dev

Model

Other

Acknowledgements

[X] I have read the above and searched for existing issues
[X] I confirm that this is classified correctly and its not an extension issue

do not download random zip files like that.

this is fixed in dev branch, service release will be soon.

this is fixed in dev branch, service release will be soon.

I don't know what a "service release" is, I am on dev branch and it doesn't seem fixed. Can you please share any specific timeline indication so I don't "git pull" every 10 minutes? :)

TY!

reopening. set env variable SD_LOAD_DEBUG=true, reproduce the issue and upload the new log - it will contain more information.

reopening. set env variable SD_LOAD_DEBUG=true, reproduce the issue and upload the new log - it will contain more information.

ok, how do I set env variable SD_LOAD_DEBUG=true?

set SD_LOAD_DEBUG=true
.\webui.bat --medvram --debug

`PS C:\ai\automatic> set SD_LOAD_DEBUG=true PS C:\ai\automatic> .\webui.bat --medvram --debug Using VENV: C:\ai\automatic\venv 19:49:35-619703 INFO Starting SD.Next 19:49:35-622696 INFO Logger: file="C:\ai\automatic\sdnext.log" level=DEBUG size=65 mode=create 19:49:35-623953 INFO Python version=3.11.9 platform=Windows bin="C:\ai\automatic\venv\Scripts\python.exe" venv="C:\ai\automatic\venv" 19:49:35-828245 INFO Version: app=sd.next updated=2024-09-03 hash=f9dcff6d branch=dev url=https://github.com/vladmandic/automatic/tree/dev ui=dev 19:49:36-666900 INFO Latest published version: bab17a0b4f91b41c885f10262ef8c8e70ba72faa 2024-08-31T20:57:34Z 19:49:36-681662 INFO Platform: arch=AMD64 cpu=Intel64 Family 6 Model 165 Stepping 5, GenuineIntel system=Windows release=Windows-10-10.0.22631-SP0 python=3.11.9 19:49:36-683856 DEBUG Setting environment tuning 19:49:36-684856 INFO HF cache folder: C:\Users\sebas.cache\huggingface\hub 19:49:36-685881 DEBUG Torch allocator: "garbage_collection_threshold:0.80,max_split_size_mb:512" 19:49:36-697378 DEBUG Torch overrides: cuda=False rocm=False ipex=False diml=False openvino=False 19:49:36-698375 DEBUG Torch allowed: cuda=True rocm=True ipex=True diml=True openvino=True 19:49:36-709863 INFO nVidia CUDA toolkit detected: nvidia-smi present 19:49:36-792917 WARNING Modified files: ['models/Reference/playgroundai--playground-v2-1024px-aesthetic.jpg'] 19:49:36-891363 INFO Verifying requirements 19:49:36-894873 INFO Verifying packages 19:49:36-937831 DEBUG Repository update time: Tue Sep 3 17:45:51 2024 19:49:36-938828 INFO Startup: standard 19:49:36-939826 INFO Verifying submodules 19:49:40-052826 DEBUG Git detached head detected: folder="extensions-builtin/sd-extension-chainner" reattach=main 19:49:40-053833 DEBUG Submodule: extensions-builtin/sd-extension-chainner / main 19:49:40-180390 DEBUG Git detached head detected: folder="extensions-builtin/sd-extension-system-info" reattach=main 19:49:40-181388 DEBUG Submodule: extensions-builtin/sd-extension-system-info / main 19:49:40-309297 DEBUG Git detached head detected: folder="extensions-builtin/sd-webui-agent-scheduler" reattach=main 19:49:40-310267 DEBUG Submodule: extensions-builtin/sd-webui-agent-scheduler / main 19:49:40-487775 DEBUG Git detached head detected: folder="extensions-builtin/sdnext-modernui" reattach=dev 19:49:40-488773 DEBUG Submodule: extensions-builtin/sdnext-modernui / dev 19:49:40-643496 DEBUG Git detached head detected: folder="extensions-builtin/stable-diffusion-webui-rembg" reattach=master 19:49:40-643496 DEBUG Submodule: extensions-builtin/stable-diffusion-webui-rembg / master 19:49:40-773368 DEBUG Git detached head detected: folder="modules/k-diffusion" reattach=master 19:49:40-774455 DEBUG Submodule: modules/k-diffusion / master 19:49:40-896987 DEBUG Git detached head detected: folder="wiki" reattach=master 19:49:40-898983 DEBUG Submodule: wiki / master 19:49:40-974823 DEBUG Register paths 19:49:41-071990 DEBUG Installed packages: 209 19:49:41-074109 DEBUG Extensions all: ['Lora', 'sd-extension-chainner', 'sd-extension-system-info', 'sd-webui-agent-scheduler', 'sd-webui-controlnet', 'sdnext-modernui', 'stable-diffusion-webui-images-browser', 'stable-diffusion-webui-rembg'] 19:49:41-259634 DEBUG Running extension installer: C:\ai\automatic\extensions-builtin\sd-extension-system-info\install.py 19:49:41-639342 DEBUG Running extension installer: C:\ai\automatic\extensions-builtin\sd-webui-agent-scheduler\install.py 19:49:42-020350 DEBUG Running extension installer: C:\ai\automatic\extensions-builtin\sd-webui-controlnet\install.py 19:49:42-561136 DEBUG Running extension installer: C:\ai\automatic\extensions-builtin\stable-diffusion-webui-images-browser\install.py 19:49:42-946570 DEBUG Running extension installer: C:\ai\automatic\extensions-builtin\stable-diffusion-webui-rembg\install.py 19:49:43-333996 DEBUG Extensions all: [] 19:49:43-334992 INFO Extensions enabled: ['Lora', 'sd-extension-chainner', 'sd-extension-system-info', 'sd-webui-agent-scheduler', 'sd-webui-controlnet', 'sdnext-modernui', 'stable-diffusion-webui-images-browser', 'stable-diffusion-webui-rembg'] 19:49:43-336987 INFO Verifying requirements 19:49:43-336987 DEBUG Setup complete without errors: 1725382183 19:49:43-344402 DEBUG Extension preload: {'extensions-builtin': 0.0, 'extensions': 0.0} 19:49:43-345399 DEBUG Starting module: <module 'webui' from 'C:\ai\automatic\webui.py'> 19:49:43-346397 INFO Command line args: ['--medvram', '--debug'] medvram=True debug=True 19:49:43-347394 DEBUG Env flags: [] 19:49:49-563062 INFO Load packages: {'torch': '2.4.0+cu124', 'diffusers': '0.31.0.dev0', 'gradio': '3.43.2'} 19:49:50-753147 DEBUG Read: file="config.json" json=35 bytes=1503 time=0.000 19:49:50-755191 DEBUG Unknown settings: ['cross_attention_options'] 19:49:50-758183 INFO Engine: backend=Backend.DIFFUSERS compute=cuda device=cuda attention="Scaled-Dot-Product" mode=no_grad 19:49:50-823069 INFO Device: device=NVIDIA GeForce RTX 4080 n=1 arch=sm_90 cap=(8, 9) cuda=12.4 cudnn=90100 driver=560.81 19:49:50-826483 DEBUG Read: file="html\reference.json" json=52 bytes=29118 time=0.001 19:49:51-270287 DEBUG ONNX: version=1.19.0 provider=CUDAExecutionProvider, available=['AzureExecutionProvider', 'CPUExecutionProvider'] 19:49:51-476149 DEBUG Importing LDM 19:49:51-495196 DEBUG Entering start sequence 19:49:51-498187 DEBUG Initializing 19:49:51-525671 INFO Available VAEs: path="models\VAE" items=0 19:49:51-527666 DEBUG Available UNets: path="models\UNET" items=0 19:49:51-529660 DEBUG Available T5s: path="models\T5" items=0 19:49:51-530657 INFO Disabled extensions: ['sd-webui-controlnet', 'sdnext-modernui'] 19:49:51-533159 DEBUG Read: file="cache.json" json=2 bytes=10089 time=0.000 19:49:51-541147 DEBUG Read: file="metadata.json" json=470 bytes=1620174 time=0.007 19:49:51-547536 DEBUG Scanning diffusers cache: folder=models\Diffusers items=2 time=0.00 19:49:51-549531 INFO Available models: path="models\Stable-diffusion" items=21 time=0.02 19:49:51-774650 DEBUG Load extensions 19:49:51-828606 INFO Extension: script='extensions-builtin\Lora\scripts\lora_script.py' [2;36m19:49:51-825613[0m[2;36m [0m[34mINFO [0m LoRA networks: [33mavailable[0m=[1;36m70[0m [33mfolders[0m=[1;36m3[0m 19:49:52-266436 INFO Extension: script='extensions-builtin\sd-webui-agent-scheduler\scripts\task_scheduler.py' Using sqlite file: extensions-builtin\sd-webui-agent-scheduler\task_scheduler.sqlite3 19:49:52-489808 DEBUG Extensions init time: 0.71 sd-webui-agent-scheduler=0.39 stable-diffusion-webui-images-browser=0.21 19:49:52-503249 DEBUG Read: file="html/upscalers.json" json=4 bytes=2672 time=0.000 19:49:52-505257 DEBUG Read: file="extensions-builtin\sd-extension-chainner\models.json" json=24 bytes=2719 time=0.000 19:49:52-507251 DEBUG chaiNNer models: path="models\chaiNNer" defined=24 discovered=0 downloaded=8 19:49:52-509245 DEBUG Upscaler type=ESRGAN folder="models\ESRGAN" model="1x-ITF-SkinDiffDetail-Lite-v1" path="models\ESRGAN\1x-ITF-SkinDiffDetail-Lite-v1.pth" 19:49:52-510242 DEBUG Upscaler type=ESRGAN folder="models\ESRGAN" model="4xNMKDSuperscale_4xNMKDSuperscale" path="models\ESRGAN\4xNMKDSuperscale_4xNMKDSuperscale.pth" 19:49:52-511241 DEBUG Upscaler type=ESRGAN folder="models\ESRGAN" model="4x_NMKD-Siax_200k" path="models\ESRGAN\4x_NMKD-Siax_200k.pth" 19:49:52-515419 DEBUG Load upscalers: total=56 downloaded=11 user=3 time=0.02 ['None', 'Lanczos', 'Nearest', 'ChaiNNer', 'AuraSR', 'ESRGAN', 'LDSR', 'RealESRGAN', 'SCUNet', 'SD', 'SwinIR'] 19:49:52-533908 DEBUG Load styles: folder="models\styles" items=288 time=0.02 19:49:52-537126 DEBUG Creating UI 19:49:52-538124 DEBUG UI themes available: type=Standard themes=12 19:49:52-539121 INFO UI theme: type=Standard name="black-teal" 19:49:52-547608 DEBUG UI theme: css="C:\ai\automatic\javascript\black-teal.css" base="sdnext.css" user="None" 19:49:52-549602 DEBUG UI initialize: txt2img 19:49:52-615207 DEBUG Networks: page='model' items=72 subfolders=2 tab=txt2img folders=['models\Stable-diffusion', 'models\Diffusers', 'models\Reference'] list=0.05 thumb=0.01 desc=0.00 info=0.00 workers=4 sort=Default 19:49:52-624200 DEBUG Networks: page='lora' items=70 subfolders=0 tab=txt2img folders=['models\Lora', 'models\LyCORIS'] list=0.05 thumb=0.01 desc=0.02 info=0.03 workers=4 sort=Default 19:49:52-657757 DEBUG Networks: page='style' items=288 subfolders=1 tab=txt2img folders=['models\styles', 'html'] list=0.04 thumb=0.00 desc=0.00 info=0.00 workers=4 sort=Default 19:49:52-663257 DEBUG Networks: page='embedding' items=13 subfolders=0 tab=txt2img folders=['models\embeddings'] list=0.03 thumb=0.01 desc=0.00 info=0.00 workers=4 sort=Default 19:49:52-665270 DEBUG Networks: page='vae' items=0 subfolders=0 tab=txt2img folders=['models\VAE'] list=0.00 thumb=0.00 desc=0.00 info=0.00 workers=4 sort=Default 19:49:52-750098 DEBUG UI initialize: img2img 19:49:53-026508 DEBUG UI initialize: control models=models\control 19:49:53-318592 DEBUG Read: file="ui-config.json" json=0 bytes=2 time=0.000 19:49:53-423146 DEBUG UI themes available: type=Standard themes=12 19:49:54-006627 DEBUG Reading failed: C:\ai\automatic\html\extensions.json [Errno 2] No such file or directory: 'C:\ai\automatic\html\extensions.json' 19:49:54-007624 INFO Extension list is empty: refresh required 19:49:54-669288 DEBUG Extension list: processed=8 installed=8 enabled=6 disabled=2 visible=8 hidden=0 19:49:55-037787 DEBUG Root paths: ['C:\ai\automatic'] 19:49:55-120858 INFO Local URL: http://127.0.0.1:7860/ 19:49:55-121855 DEBUG Gradio functions: registered=2364 19:49:55-123361 DEBUG FastAPI middleware: ['Middleware', 'Middleware'] 19:49:55-126652 DEBUG Creating API 19:49:55-306381 INFO [AgentScheduler] Task queue is empty 19:49:55-307355 INFO [AgentScheduler] Registering APIs 19:49:55-438287 DEBUG Scripts setup: ['IP Adapters:0.025', 'AnimateDiff:0.009', 'X/Y/Z Grid:0.011', 'Face:0.013', 'Image-to-Video:0.006'] 19:49:55-439285 DEBUG Model metadata: file="metadata.json" no changes 19:49:55-441280 DEBUG Torch mode: deterministic=False 19:49:55-476612 INFO Torch override VAE dtype: no-half set 19:49:55-477609 DEBUG Desired Torch parameters: dtype=FP16 no-half=False no-half-vae=True upscast=False 19:49:55-478607 INFO Setting Torch parameters: device=cuda dtype=torch.float16 vae=torch.float32 unet=torch.float16 context=no_grad fp16=True bf16=None optimization=Scaled-Dot-Product 19:49:55-480602 DEBUG Model requested: fn= 19:49:55-481601 INFO Select: model="epicrealismXL_v8Kiss [04639d4084]" 19:49:55-484118 DEBUG Load model: existing=False target=C:\ai\automatic\models\Stable-diffusion\epicrealismXL_v8Kiss.safetensors info=None 19:49:55-485593 DEBUG Diffusers loading: path="C:\ai\automatic\models\Stable-diffusion\epicrealismXL_v8Kiss.safetensors" 19:49:55-486590 INFO Autodetect: model="Stable Diffusion XL" class=StableDiffusionXLPipeline file="C:\ai\automatic\models\Stable-diffusion\epicrealismXL_v8Kiss.safetensors" size=6617MB Fetching 17 files: 100%|███████████████████████████████████████████████████████████████████████| 17/17 [00:00<?, ?it/s] Loading pipeline components... 100% ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 7/7 [ 0:00:01 < 0:00:00 , 6 C/s ] 19:49:57-388332 DEBUG Setting model: pipeline=StableDiffusionXLPipeline config={'low_cpu_mem_usage': True, 'torch_dtype': torch.float16, 'load_connected_pipeline': True, 'extract_ema': False, 'use_safetensors': True, 'cache_dir': 'C:\Users\sebas\.cache\huggingface\hub'} 19:50:01-105555 INFO Load embeddings: loaded=2 skipped=11 time=3.72 19:50:01-345807 DEBUG Setting model VAE: no-half=True 19:50:01-346805 DEBUG Setting model: slicing=True 19:50:01-347802 DEBUG Setting model: tiling=True 19:50:01-348799 DEBUG Setting model: attention=Scaled-Dot-Product 19:50:01-369781 DEBUG Setting model: offload=model 19:50:01-408992 DEBUG Read: file="C:\ai\automatic\configs\sdxl\vae\config.json" json=15 bytes=674 time=0.000 19:50:01-646005 DEBUG GC: utilization={'gpu': 8, 'ram': 4, 'threshold': 80} gc={'collected': 305, 'saved': 0.0} before={'gpu': 1.33, 'ram': 2.48} after={'gpu': 1.33, 'ram': 2.48, 'retries': 0, 'oom': 0} device=cuda fn=load_diffuser time=0.23 19:50:01-656505 INFO Load model: time=5.93 load=1.90 embeddings=3.72 options=0.26 native=1024 {'ram': {'used': 2.48, 'total': 63.92}, 'gpu': {'used': 1.33, 'total': 15.99}, 'retries': 0, 'oom': 0} 19:50:01-659497 DEBUG Script callback init time: image_browser.py:ui_tabs=0.43 system-info.py:app_started=0.07 task_scheduler.py:app_started=0.15 19:50:01-661491 DEBUG Save: file="config.json" json=35 bytes=1456 time=0.002 19:50:01-661491 INFO Startup time: 18.31 torch=4.34 gradio=1.42 diffusers=0.46 libraries=1.91 extensions=0.71 face-restore=0.23 ui-en=0.23 ui-txt2img=0.06 ui-img2img=0.24 ui-control=0.12 ui-settings=0.25 ui-extensions=1.14 ui-defaults=0.29 launch=0.14 api=0.10 app-started=0.21 checkpoint=6.22 19:50:01-664988 DEBUG Unused settings: ['cross_attention_options'] 19:51:32-202282 INFO Select: model="Diffusers\Disty0/FLUX.1-dev-qint4 [82811df42b]" 19:51:32-204276 DEBUG Load model: existing=False target=models\Diffusers\models--Disty0--FLUX.1-dev-qint4\snapshots\82811df42b556a1153b971d8375d 5170c306a6eb info=None 19:51:32-585594 DEBUG GC: utilization={'gpu': 8, 'ram': 3, 'threshold': 80} gc={'collected': 381, 'saved': 0.0} before={'gpu': 1.33, 'ram': 1.83} after={'gpu': 1.33, 'ram': 1.83, 'retries': 0, 'oom': 0} device=cuda fn=unload_modelweights time=0.24 19:51:32-587593 DEBUG Unload weights model: {'ram': {'used': 1.83, 'total': 63.92}, 'gpu': {'used': 1.33, 'total': 15.99}, 'retries': 0, 'oom': 0} 19:51:32-596091 DEBUG Diffusers loading: path="models\Diffusers\models--Disty0--FLUX.1-dev-qint4\snapshots\82811df42b556a1153b971d8375d5 170c306a6eb" 19:51:32-598088 INFO Autodetect: model="FLUX" class=FluxPipeline file="models\Diffusers\models--Disty0--FLUX.1-dev-qint4\snapshots\82811df42b556a1153b971d8375d5 170c306a6eb" size=0MB 19:51:32-604071 DEBUG Loading FLUX: model="Diffusers\Disty0/FLUX.1-dev-qint4" unet="None" t5="None" vae="None" quant=qint4 offload=model dtype=torch.float16 19:51:33-156265 ERROR Loading FLUX: Failed to load Quanto transformer: Repo id must use alphanumeric chars or '-', '', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is 96: 'Diffusers\Disty0/FLUX.1-dev-qint4'. 19:51:33-158259 ERROR FLUX Quanto:: HFValidationError ╭───────────────────────────────────────── Traceback (most recent call last) ──────────────────────────────────────────╮ │ C:\ai\automatic\modules\model_flux.py:50 in load_flux_quanto │ │ │ │ 49 │ │ │ repo_id = checkpoint_info.name.replace('Diffusers/', '') │ │ ❱ 50 │ │ │ quantization_map = hf_hub_download(repo_id, subfolder='transformer', filename='quantization_map.js │ │ 51 │ │ with open(quantization_map, "r", encoding='utf8') as f: │ │ │ │ C:\ai\automatic\venv\Lib\site-packages\huggingface_hub\utils_deprecation.py:101 in inner_f │ │ │ │ 100 │ │ │ │ warnings.warn(message, FutureWarning) │ │ ❱ 101 │ │ │ return f(*args, *kwargs) │ │ 102 │ │ │ │ C:\ai\automatic\venv\Lib\site-packages\huggingface_hub\utils_validators.py:106 in _inner_fn │ │ │ │ 105 │ │ │ if arg_name in ["repo_id", "from_id", "to_id"]: │ │ ❱ 106 │ │ │ │ validate_repo_id(arg_value) │ │ 107 │ │ │ │ C:\ai\automatic\venv\Lib\site-packages\huggingface_hub\utils_validators.py:160 in validate_repo_id │ │ │ │ 159 │ if not REPO_ID_REGEX.match(repoid): │ │ ❱ 160 │ │ raise HFValidationError( │ │ 161 │ │ │ "Repo id must use alphanumeric chars or '-', '', '.', '--' and '..' are" │ ╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯ HFValidationError: Repo id must use alphanumeric chars or '-', '', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is 96: 'Diffusers\Disty0/FLUX.1-dev-qint4'. 19:51:33-219179 ERROR Loading FLUX: Failed to load Quanto text encoder: Repo id must use alphanumeric chars or '-', '', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is 96: 'Diffusers\Disty0/FLUX.1-dev-qint4'. 19:51:33-220176 ERROR FLUX Quanto:: HFValidationError ╭───────────────────────────────────────── Traceback (most recent call last) ──────────────────────────────────────────╮ │ C:\ai\automatic\modules\model_flux.py:74 in load_flux_quanto │ │ │ │ 73 │ │ │ repo_id = checkpoint_info.name.replace('Diffusers/', '') │ │ ❱ 74 │ │ │ quantization_map = hf_hub_download(repo_id, subfolder='text_encoder_2', filename='quantization_map │ │ 75 │ │ with open(quantization_map, "r", encoding='utf8') as f: │ │ │ │ C:\ai\automatic\venv\Lib\site-packages\huggingface_hub\utils_deprecation.py:101 in inner_f │ │ │ │ 100 │ │ │ │ warnings.warn(message, FutureWarning) │ │ ❱ 101 │ │ │ return f(args, **kwargs) │ │ 102 │ │ │ │ C:\ai\automatic\venv\Lib\site-packages\huggingface_hub\utils_validators.py:106 in _inner_fn │ │ │ │ 105 │ │ │ if arg_name in ["repo_id", "from_id", "to_id"]: │ │ ❱ 106 │ │ │ │ validate_repo_id(arg_value) │ │ 107 │ │ │ │ C:\ai\automatic\venv\Lib\site-packages\huggingface_hub\utils_validators.py:160 in validate_repo_id │ │ │ │ 159 │ if not REPO_ID_REGEX.match(repoid): │ │ ❱ 160 │ │ raise HFValidationError( │ │ 161 │ │ │ "Repo id must use alphanumeric chars or '-', '', '.', '--' and '..' are" │ ╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯ HFValidationError: Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is 96: 'Diffusers\Disty0/FLUX.1-dev-qint4'. 19:51:33-244349 DEBUG Loading FLUX: preloaded=[] Loading pipeline components... 43% ━━━━━━━━━━━━━━━━━━━━━╺━━━━━━━━━━━━━━━━━━━━━━━━━━━ 3/7 [ 0:00:25 < 0:00:01 , 5 C/s ]19:51:59-766344 DEBUG Server: alive=True jobs=1 requests=7 uptime=130 memory=16.78/63.92 backend=Backend.DIFFUSERS state=idle

Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] [A

Loading checkpoint shards: 50%|############################5 | 1/2 [00:09<00:09, 9.61s/it] [A

Loading checkpoint shards: 100%|#########################################################| 2/2 [00:18<00:00, 9.05s/it] [A Loading checkpoint shards: 100%|#########################################################| 2/2 [00:18<00:00, 9.14s/it]

Loading pipeline components... 100% ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 7/7 [ 0:01:05 < 0:00:00 , 0 C/s ] 19:52:39-336579 INFO Load embeddings: loaded=0 skipped=13 time=0.03 19:52:39-426564 DEBUG Setting model VAE: no-half=True 19:52:39-428818 DEBUG Setting model: slicing=True 19:52:39-429815 DEBUG Setting model: tiling=True 19:52:39-430812 DEBUG Setting model: attention=Scaled-Dot-Product 19:52:39-448413 DEBUG Setting model: offload=model 19:52:39-742676 DEBUG GC: utilization={'gpu': 8, 'ram': 54, 'threshold': 80} gc={'collected': 304, 'saved': 0.0} before={'gpu': 1.33, 'ram': 34.68} after={'gpu': 1.33, 'ram': 34.68, 'retries': 0, 'oom': 0} device=cuda fn=load_diffuser time=0.26 19:52:39-744670 INFO Load model: time=66.88 load=66.71 options=0.11 native=1024 {'ram': {'used': 34.68, 'total': 63.92}, 'gpu': {'used': 1.33, 'total': 15.99}, 'retries': 0, 'oom': 0} 19:52:39-746665 DEBUG Setting changed: sd_model_checkpoint=Diffusers\Disty0/FLUX.1-dev-qint4 [82811df42b] progress=True 19:52:39-749023 DEBUG Save: file="config.json" json=35 bytes=1408 time=0.002 19:52:39-751017 DEBUG Unused settings: ['cross_attention_options'] `

ah, powershell, not cmd....great... try

[System.Environment]::SetEnvironmentVariable('SD_LOAD_DEBUG','true')
.\webui.bat --medvram --debug

or just use set as i've mentioned above from cmd.exe

This is with CMD. It seems to set the variable but for myself I don't see any additional information. I hope I'm wrong and you see something relevant

_06:13:59-974905 DEBUG Env flags: ['SD_LOADDEBUG=true']

I am not clear why it says "size=0MB" though, that seems odd

06:14:22-160028 INFO Autodetect: model="FLUX" class=FluxPipeline file="models\Diffusers\models--Disty0--FLUX.1-dev-qint4\snapshots\82811df42b556a1153b971d8375d5 170c306a6eb" size=0MB

c:\ai\automatic>set SD_LOAD_DEBUG=true

c:\ai\automatic>.\webui.bat --medvram --debug
Using VENV: c:\ai\automatic\venv
06:13:51-592018 INFO     Starting SD.Next
06:13:51-595756 INFO     Logger: file="c:\ai\automatic\sdnext.log" level=DEBUG size=65 mode=create
06:13:51-596581 INFO     Python version=3.11.9 platform=Windows bin="c:\ai\automatic\venv\Scripts\python.exe"
                         venv="c:\ai\automatic\venv"
06:13:51-837543 INFO     Version: app=sd.next updated=2024-09-03 hash=f9dcff6d branch=dev
                         url=https://github.com/vladmandic/automatic/tree/dev ui=dev
06:13:52-811714 INFO     Latest published version: bab17a0b4f91b41c885f10262ef8c8e70ba72faa 2024-08-31T20:57:34Z
06:13:52-828162 INFO     Platform: arch=AMD64 cpu=Intel64 Family 6 Model 165 Stepping 5, GenuineIntel system=Windows
                         release=Windows-10-10.0.22631-SP0 python=3.11.9
06:13:52-830158 DEBUG    Setting environment tuning
06:13:52-831154 INFO     HF cache folder: C:\Users\sebas\.cache\huggingface\hub
06:13:52-832152 DEBUG    Torch allocator: "garbage_collection_threshold:0.80,max_split_size_mb:512"
06:13:52-845303 DEBUG    Torch overrides: cuda=False rocm=False ipex=False diml=False openvino=False
06:13:52-846300 DEBUG    Torch allowed: cuda=True rocm=True ipex=True diml=True openvino=True
06:13:52-856833 INFO     nVidia CUDA toolkit detected: nvidia-smi present
06:13:53-003181 WARNING  Modified files: ['models/Reference/playgroundai--playground-v2-1024px-aesthetic.jpg']
06:13:53-102568 INFO     Verifying requirements
06:13:53-106574 INFO     Verifying packages
06:13:53-150811 DEBUG    Repository update time: Tue Sep  3 17:45:51 2024
06:13:53-151808 INFO     Startup: standard
06:13:53-152806 INFO     Verifying submodules
06:13:56-630020 DEBUG    Git detached head detected: folder="extensions-builtin/sd-extension-chainner" reattach=main
06:13:56-632015 DEBUG    Submodule: extensions-builtin/sd-extension-chainner / main
06:13:56-756354 DEBUG    Git detached head detected: folder="extensions-builtin/sd-extension-system-info" reattach=main
06:13:56-757355 DEBUG    Submodule: extensions-builtin/sd-extension-system-info / main
06:13:56-884085 DEBUG    Git detached head detected: folder="extensions-builtin/sd-webui-agent-scheduler" reattach=main
06:13:56-886071 DEBUG    Submodule: extensions-builtin/sd-webui-agent-scheduler / main
06:13:57-059945 DEBUG    Git detached head detected: folder="extensions-builtin/sdnext-modernui" reattach=dev
06:13:57-060945 DEBUG    Submodule: extensions-builtin/sdnext-modernui / dev
06:13:57-212641 DEBUG    Git detached head detected: folder="extensions-builtin/stable-diffusion-webui-rembg"
                         reattach=master
06:13:57-214606 DEBUG    Submodule: extensions-builtin/stable-diffusion-webui-rembg / master
06:13:57-339171 DEBUG    Git detached head detected: folder="modules/k-diffusion" reattach=master
06:13:57-340169 DEBUG    Submodule: modules/k-diffusion / master
06:13:57-468990 DEBUG    Git detached head detected: folder="wiki" reattach=master
06:13:57-470985 DEBUG    Submodule: wiki / master
06:13:57-614722 DEBUG    Register paths
06:13:57-710002 DEBUG    Installed packages: 209
06:13:57-711972 DEBUG    Extensions all: ['Lora', 'sd-extension-chainner', 'sd-extension-system-info',
                         'sd-webui-agent-scheduler', 'sd-webui-controlnet', 'sdnext-modernui',
                         'stable-diffusion-webui-images-browser', 'stable-diffusion-webui-rembg']
06:13:57-900076 DEBUG    Running extension installer:
                         C:\ai\automatic\extensions-builtin\sd-extension-system-info\install.py
06:13:58-287383 DEBUG    Running extension installer:
                         C:\ai\automatic\extensions-builtin\sd-webui-agent-scheduler\install.py
06:13:58-667676 DEBUG    Running extension installer: C:\ai\automatic\extensions-builtin\sd-webui-controlnet\install.py
06:13:59-201435 DEBUG    Running extension installer:
                         C:\ai\automatic\extensions-builtin\stable-diffusion-webui-images-browser\install.py
06:13:59-580423 DEBUG    Running extension installer:
                         C:\ai\automatic\extensions-builtin\stable-diffusion-webui-rembg\install.py
06:13:59-957508 DEBUG    Extensions all: []
06:13:59-957948 INFO     Extensions enabled: ['Lora', 'sd-extension-chainner', 'sd-extension-system-info',
                         'sd-webui-agent-scheduler', 'sd-webui-controlnet', 'sdnext-modernui',
                         'stable-diffusion-webui-images-browser', 'stable-diffusion-webui-rembg']
06:13:59-959945 INFO     Verifying requirements
06:13:59-960943 DEBUG    Setup complete without errors: 1725419640
06:13:59-971914 DEBUG    Extension preload: {'extensions-builtin': 0.01, 'extensions': 0.0}
06:13:59-972911 DEBUG    Starting module: <module 'webui' from 'c:\\ai\\automatic\\webui.py'>
06:13:59-973908 INFO     Command line args: ['--medvram', '--debug'] medvram=True debug=True
06:13:59-974905 DEBUG    Env flags: ['SD_LOAD_DEBUG=true']
06:14:12-825511 INFO     Load packages: {'torch': '2.4.0+cu124', 'diffusers': '0.31.0.dev0', 'gradio': '3.43.2'}
06:14:14-614189 DEBUG    Read: file="config.json" json=35 bytes=1455 time=0.000
06:14:14-616343 DEBUG    Unknown settings: ['cross_attention_options']
06:14:14-618730 INFO     Engine: backend=Backend.DIFFUSERS compute=cuda device=cuda attention="Scaled-Dot-Product"
                         mode=no_grad
06:14:14-688554 INFO     Device: device=NVIDIA GeForce RTX 4080 n=1 arch=sm_90 cap=(8, 9) cuda=12.4 cudnn=90100
                         driver=560.81
06:14:14-692515 DEBUG    Read: file="html\reference.json" json=52 bytes=29118 time=0.002
06:14:15-770849 DEBUG    ONNX: version=1.19.0 provider=CUDAExecutionProvider, available=['AzureExecutionProvider',
                         'CPUExecutionProvider']
06:14:16-198852 DEBUG    Importing LDM
06:14:16-236482 DEBUG    Entering start sequence
06:14:16-239722 DEBUG    Initializing
06:14:16-309066 INFO     Available VAEs: path="models\VAE" items=0
06:14:16-310973 DEBUG    Available UNets: path="models\UNET" items=0
06:14:16-311970 DEBUG    Available T5s: path="models\T5" items=0
06:14:16-312968 INFO     Disabled extensions: ['sd-webui-controlnet', 'sdnext-modernui']
06:14:16-322196 DEBUG    Read: file="cache.json" json=2 bytes=10089 time=0.001
06:14:16-331171 DEBUG    Read: file="metadata.json" json=470 bytes=1620174 time=0.007
06:14:16-435287 DEBUG    Scanning diffusers cache: folder=models\Diffusers items=2 time=0.00
06:14:16-437281 INFO     Available models: path="models\Stable-diffusion" items=21 time=0.12
06:14:17-249884 DEBUG    Load extensions
06:14:17-833306 INFO     Extension: script='extensions-builtin\Lora\scripts\lora_script.py'
                         [2;36m06:14:17-826945[0m[2;36m [0m[34mINFO    [0m LoRA networks: [33mavailable[0m=[1;36m70[0m
                         [33mfolders[0m=[1;36m2[0m
06:14:18-921005 INFO     Extension: script='extensions-builtin\sd-webui-agent-scheduler\scripts\task_scheduler.py' Using
                         sqlite file: extensions-builtin\sd-webui-agent-scheduler\task_scheduler.sqlite3
06:14:19-222551 DEBUG    Extensions init time: 1.97 Lora=0.50 sd-extension-chainner=0.09 sd-webui-agent-scheduler=0.98
                         stable-diffusion-webui-images-browser=0.28
06:14:19-258552 DEBUG    Read: file="html/upscalers.json" json=4 bytes=2672 time=0.000
06:14:19-262356 DEBUG    Read: file="extensions-builtin\sd-extension-chainner\models.json" json=24 bytes=2719 time=0.001
06:14:19-266249 DEBUG    chaiNNer models: path="models\chaiNNer" defined=24 discovered=0 downloaded=8
06:14:19-268245 DEBUG    Upscaler type=ESRGAN folder="models\ESRGAN" model="1x-ITF-SkinDiffDetail-Lite-v1"
                         path="models\ESRGAN\1x-ITF-SkinDiffDetail-Lite-v1.pth"
06:14:19-269242 DEBUG    Upscaler type=ESRGAN folder="models\ESRGAN" model="4xNMKDSuperscale_4xNMKDSuperscale"
                         path="models\ESRGAN\4xNMKDSuperscale_4xNMKDSuperscale.pth"
06:14:19-270241 DEBUG    Upscaler type=ESRGAN folder="models\ESRGAN" model="4x_NMKD-Siax_200k"
                         path="models\ESRGAN\4x_NMKD-Siax_200k.pth"
06:14:19-273231 DEBUG    Load upscalers: total=56 downloaded=11 user=3 time=0.05 ['None', 'Lanczos', 'Nearest',
                         'ChaiNNer', 'AuraSR', 'ESRGAN', 'LDSR', 'RealESRGAN', 'SCUNet', 'SD', 'SwinIR']
06:14:19-294380 DEBUG    Load styles: folder="models\styles" items=288 time=0.02
06:14:19-300981 DEBUG    Creating UI
06:14:19-302567 DEBUG    UI themes available: type=Standard themes=12
06:14:19-303564 INFO     UI theme: type=Standard name="black-teal"
06:14:19-311542 DEBUG    UI theme: css="C:\ai\automatic\javascript\black-teal.css" base="sdnext.css" user="None"
06:14:19-314935 DEBUG    UI initialize: txt2img
06:14:19-377925 DEBUG    Networks: page='model' items=72 subfolders=2 tab=txt2img folders=['models\\Stable-diffusion',
                         'models\\Diffusers', 'models\\Reference'] list=0.04 thumb=0.01 desc=0.01 info=0.00 workers=4
                         sort=Default
06:14:19-386901 DEBUG    Networks: page='lora' items=70 subfolders=0 tab=txt2img folders=['models\\Lora',
                         'models\\LyCORIS'] list=0.04 thumb=0.01 desc=0.02 info=0.03 workers=4 sort=Default
06:14:19-419813 DEBUG    Networks: page='style' items=288 subfolders=1 tab=txt2img folders=['models\\styles', 'html']
                         list=0.04 thumb=0.00 desc=0.00 info=0.00 workers=4 sort=Default
06:14:19-424799 DEBUG    Networks: page='embedding' items=13 subfolders=0 tab=txt2img folders=['models\\embeddings']
                         list=0.02 thumb=0.01 desc=0.00 info=0.00 workers=4 sort=Default
06:14:19-426793 DEBUG    Networks: page='vae' items=0 subfolders=0 tab=txt2img folders=['models\\VAE'] list=0.00
                         thumb=0.00 desc=0.00 info=0.00 workers=4 sort=Default
06:14:19-505574 DEBUG    UI initialize: img2img
06:14:19-605194 DEBUG    UI initialize: control models=models\control
06:14:19-880172 DEBUG    Read: file="ui-config.json" json=0 bytes=2 time=0.001
06:14:19-979737 DEBUG    UI themes available: type=Standard themes=12
06:14:20-696738 DEBUG    Reading failed: C:\ai\automatic\html\extensions.json [Errno 2] No such file or directory:
                         'C:\\ai\\automatic\\html\\extensions.json'
06:14:20-698627 INFO     Extension list is empty: refresh required
06:14:21-289137 DEBUG    Extension list: processed=8 installed=8 enabled=6 disabled=2 visible=8 hidden=0
06:14:21-455240 DEBUG    Root paths: ['c:\\ai\\automatic']
06:14:21-560365 INFO     Local URL: http://127.0.0.1:7860/
06:14:21-561362 DEBUG    Gradio functions: registered=2364
06:14:21-564422 DEBUG    FastAPI middleware: ['Middleware', 'Middleware']
06:14:21-567416 DEBUG    Creating API
06:14:21-735966 INFO     [AgentScheduler] Task queue is empty
06:14:21-737960 INFO     [AgentScheduler] Registering APIs
06:14:22-071070 DEBUG    Scripts setup: ['IP Adapters:0.022', 'AnimateDiff:0.009', 'X/Y/Z Grid:0.01', 'Face:0.013',
                         'Image-to-Video:0.006']
06:14:22-114124 DEBUG    Save: file="metadata.json" json=559 bytes=1813560 time=0.041
06:14:22-115490 INFO     Model metadata saved: file="metadata.json" items=89 time=1.88
06:14:22-116490 DEBUG    Torch mode: deterministic=False
06:14:22-150054 INFO     Torch override VAE dtype: no-half set
06:14:22-151052 DEBUG    Desired Torch parameters: dtype=FP16 no-half=False no-half-vae=True upscast=False
06:14:22-152049 INFO     Setting Torch parameters: device=cuda dtype=torch.float16 vae=torch.float32 unet=torch.float16
                         context=no_grad fp16=True bf16=None optimization=Scaled-Dot-Product
06:14:22-154044 DEBUG    Model requested: fn=<lambda>
06:14:22-155041 INFO     Select: model="Diffusers\Disty0/FLUX.1-dev-qint4 [82811df42b]"
06:14:22-157036 DEBUG    Load model: existing=False
                         target=models\Diffusers\models--Disty0--FLUX.1-dev-qint4\snapshots\82811df42b556a1153b971d8375d
                         5170c306a6eb info=None
06:14:22-159030 DEBUG    Diffusers loading:
                         path="models\Diffusers\models--Disty0--FLUX.1-dev-qint4\snapshots\82811df42b556a1153b971d8375d5
                         170c306a6eb"
06:14:22-160028 INFO     Autodetect: model="FLUX" class=FluxPipeline
                         file="models\Diffusers\models--Disty0--FLUX.1-dev-qint4\snapshots\82811df42b556a1153b971d8375d5
                         170c306a6eb" size=0MB
06:14:22-165194 DEBUG    Loading FLUX: model="Diffusers\Disty0/FLUX.1-dev-qint4" unet="None" t5="None" vae="None"
                         quant=qint4 offload=model dtype=torch.float16
06:14:22-687065 ERROR    Loading FLUX: Failed to load Quanto transformer: Repo id must use alphanumeric chars or '-',
                         '_', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is
                         96: 'Diffusers\Disty0/FLUX.1-dev-qint4'.
06:14:22-688910 ERROR    FLUX Quanto:: HFValidationError
╭───────────────────────────────────────── Traceback (most recent call last) ──────────────────────────────────────────╮
│ C:\ai\automatic\modules\model_flux.py:50 in load_flux_quanto                                                         │
│                                                                                                                      │
│    49 │   │   │   repo_id = checkpoint_info.name.replace('Diffusers/', '')                                           │
│ ❱  50 │   │   │   quantization_map = hf_hub_download(repo_id, subfolder='transformer', filename='quantization_map.js │
│    51 │   │   with open(quantization_map, "r", encoding='utf8') as f:                                                │
│                                                                                                                      │
│ c:\ai\automatic\venv\Lib\site-packages\huggingface_hub\utils\_deprecation.py:101 in inner_f                          │
│                                                                                                                      │
│   100 │   │   │   │   warnings.warn(message, FutureWarning)                                                          │
│ ❱ 101 │   │   │   return f(*args, **kwargs)                                                                          │
│   102                                                                                                                │
│                                                                                                                      │
│ c:\ai\automatic\venv\Lib\site-packages\huggingface_hub\utils\_validators.py:106 in _inner_fn                         │
│                                                                                                                      │
│   105 │   │   │   if arg_name in ["repo_id", "from_id", "to_id"]:                                                    │
│ ❱ 106 │   │   │   │   validate_repo_id(arg_value)                                                                    │
│   107                                                                                                                │
│                                                                                                                      │
│ c:\ai\automatic\venv\Lib\site-packages\huggingface_hub\utils\_validators.py:160 in validate_repo_id                  │
│                                                                                                                      │
│   159 │   if not REPO_ID_REGEX.match(repo_id):                                                                       │
│ ❱ 160 │   │   raise HFValidationError(                                                                               │
│   161 │   │   │   "Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are"                          │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
HFValidationError: Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is 96: 'Diffusers\Disty0/FLUX.1-dev-qint4'.
06:14:22-743187 ERROR    Loading FLUX: Failed to load Quanto text encoder: Repo id must use alphanumeric chars or '-',
                         '_', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is
                         96: 'Diffusers\Disty0/FLUX.1-dev-qint4'.
06:14:22-744666 ERROR    FLUX Quanto:: HFValidationError
╭───────────────────────────────────────── Traceback (most recent call last) ──────────────────────────────────────────╮
│ C:\ai\automatic\modules\model_flux.py:74 in load_flux_quanto                                                         │
│                                                                                                                      │
│    73 │   │   │   repo_id = checkpoint_info.name.replace('Diffusers/', '')                                           │
│ ❱  74 │   │   │   quantization_map = hf_hub_download(repo_id, subfolder='text_encoder_2', filename='quantization_map │
│    75 │   │   with open(quantization_map, "r", encoding='utf8') as f:                                                │
│                                                                                                                      │
│ c:\ai\automatic\venv\Lib\site-packages\huggingface_hub\utils\_deprecation.py:101 in inner_f                          │
│                                                                                                                      │
│   100 │   │   │   │   warnings.warn(message, FutureWarning)                                                          │
│ ❱ 101 │   │   │   return f(*args, **kwargs)                                                                          │
│   102                                                                                                                │
│                                                                                                                      │
│ c:\ai\automatic\venv\Lib\site-packages\huggingface_hub\utils\_validators.py:106 in _inner_fn                         │
│                                                                                                                      │
│   105 │   │   │   if arg_name in ["repo_id", "from_id", "to_id"]:                                                    │
│ ❱ 106 │   │   │   │   validate_repo_id(arg_value)                                                                    │
│   107                                                                                                                │
│                                                                                                                      │
│ c:\ai\automatic\venv\Lib\site-packages\huggingface_hub\utils\_validators.py:160 in validate_repo_id                  │
│                                                                                                                      │
│   159 │   if not REPO_ID_REGEX.match(repo_id):                                                                       │
│ ❱ 160 │   │   raise HFValidationError(                                                                               │
│   161 │   │   │   "Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are"                          │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
HFValidationError: Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is 96: 'Diffusers\Disty0/FLUX.1-dev-qint4'.
06:14:22-767879 DEBUG    Loading FLUX: preloaded=[]

Loading checkpoint shards:   0%|                                                                 | 0/2 [00:00<?, ?it/s]
[A

Loading checkpoint shards:  50%|############################5                            | 1/2 [00:09<00:09,  9.62s/it]
[A

Loading checkpoint shards: 100%|#########################################################| 2/2 [00:17<00:00,  8.85s/it]
[A
Loading checkpoint shards: 100%|#########################################################| 2/2 [00:17<00:00,  8.97s/it]

Loading pipeline components... 100% ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 7/7  [ 0:01:02 < 0:00:00 , 0 C/s ]
06:15:26-090091 INFO     Load embeddings: loaded=0 skipped=13 time=0.05
06:15:26-171873 DEBUG    Setting model VAE: no-half=True
06:15:26-172870 DEBUG    Setting model: slicing=True
06:15:26-173867 DEBUG    Setting model: tiling=True
06:15:26-174865 DEBUG    Setting model: attention=Scaled-Dot-Product
06:15:26-195809 DEBUG    Setting model: offload=model
06:15:26-444412 DEBUG    GC: utilization={'gpu': 8, 'ram': 54, 'threshold': 80} gc={'collected': 305, 'saved': 0.0}
                         before={'gpu': 1.33, 'ram': 34.56} after={'gpu': 1.33, 'ram': 34.56, 'retries': 0, 'oom': 0}
                         device=cuda fn=load_diffuser time=0.22
06:15:26-446409 INFO     Load model: time=64.07 load=63.88 embeddings=0.05 options=0.10 native=1024 {'ram': {'used':
                         34.56, 'total': 63.92}, 'gpu': {'used': 1.33, 'total': 15.99}, 'retries': 0, 'oom': 0}
06:15:26-449333 DEBUG    Script callback init time: image_browser.py:ui_tabs=0.57 system-info.py:app_started=0.06
                         task_scheduler.py:app_started=0.35
06:15:26-450299 INFO     Startup time: 86.47 torch=8.43 gradio=2.46 diffusers=1.95 libraries=3.37 samplers=0.07
                         extensions=1.97 models=0.12 face-restore=0.81 upscalers=0.05 ui-en=0.22 ui-txt2img=0.06
                         ui-img2img=0.06 ui-control=0.11 ui-settings=0.24 ui-extensions=1.20 ui-defaults=0.09
                         launch=0.16 api=0.09 app-started=0.41 checkpoint=64.38
06:15:26-452294 DEBUG    Save: file="config.json" json=35 bytes=1408 time=0.003
06:15:26-455284 DEBUG    Unused settings: ['cross_attention_options']
06:16:00-466853 DEBUG    Server: alive=True jobs=1 requests=1 uptime=107 memory=34.56/63.92 backend=Backend.DIFFUSERS
                         state=idle

hopefully should be fixed now in dev - if its not, update here (with new logs) and i'll reopen the issue.

hopefully should be fixed now in dev - if its not, update here (with new logs) and i'll reopen the issue.

Doesn't seem solved to me, it persists. The only change I see is that it does not fall back automatically to flux-dev, it just fails

Want me to try and re-download the model?


c:\ai\automatic>.\webui.bat --medvram --debug
Using VENV: c:\ai\automatic\venv
17:02:19-522979 INFO     Starting SD.Next
17:02:19-526505 INFO     Logger: file="c:\ai\automatic\sdnext.log" level=DEBUG size=65 mode=create
17:02:19-527503 INFO     Python version=3.11.9 platform=Windows bin="c:\ai\automatic\venv\Scripts\python.exe"
                         venv="c:\ai\automatic\venv"
17:02:19-730245 INFO     Version: app=sd.next updated=2024-09-04 hash=a1b67020 branch=dev
                         url=https://github.com/vladmandic/automatic/tree/dev ui=dev
17:02:20-583934 INFO     Latest published version: bab17a0b4f91b41c885f10262ef8c8e70ba72faa 2024-08-31T20:57:34Z
17:02:20-599085 INFO     Platform: arch=AMD64 cpu=Intel64 Family 6 Model 165 Stepping 5, GenuineIntel system=Windows
                         release=Windows-10-10.0.22631-SP0 python=3.11.9
17:02:20-601079 DEBUG    Setting environment tuning
17:02:20-602076 INFO     HF cache folder: C:\Users\sebas\.cache\huggingface\hub
17:02:20-603073 DEBUG    Torch allocator: "garbage_collection_threshold:0.80,max_split_size_mb:512"
17:02:20-613047 DEBUG    Torch overrides: cuda=False rocm=False ipex=False diml=False openvino=False
17:02:20-615041 DEBUG    Torch allowed: cuda=True rocm=True ipex=True diml=True openvino=True
17:02:20-625043 INFO     nVidia CUDA toolkit detected: nvidia-smi present
17:02:20-711753 WARNING  Modified files: ['models/Reference/playgroundai--playground-v2-1024px-aesthetic.jpg']
17:02:20-805499 INFO     Verifying requirements
17:02:20-809366 INFO     Verifying packages
17:02:20-853313 DEBUG    Repository update time: Wed Sep  4 16:32:08 2024
17:02:20-854310 INFO     Startup: standard
17:02:20-855308 INFO     Verifying submodules
17:02:24-073925 DEBUG    Git detached head detected: folder="extensions-builtin/sd-extension-chainner" reattach=main
17:02:24-075892 DEBUG    Submodule: extensions-builtin/sd-extension-chainner / main
17:02:24-201080 DEBUG    Git detached head detected: folder="extensions-builtin/sd-extension-system-info" reattach=main
17:02:24-202078 DEBUG    Submodule: extensions-builtin/sd-extension-system-info / main
17:02:24-327422 DEBUG    Git detached head detected: folder="extensions-builtin/sd-webui-agent-scheduler" reattach=main
17:02:24-328419 DEBUG    Submodule: extensions-builtin/sd-webui-agent-scheduler / main
17:02:24-502986 DEBUG    Git detached head detected: folder="extensions-builtin/sdnext-modernui" reattach=dev
17:02:24-503983 DEBUG    Submodule: extensions-builtin/sdnext-modernui / dev
17:02:24-649832 DEBUG    Git detached head detected: folder="extensions-builtin/stable-diffusion-webui-rembg"
                         reattach=master
17:02:24-650856 DEBUG    Submodule: extensions-builtin/stable-diffusion-webui-rembg / master
17:02:24-773333 DEBUG    Git detached head detected: folder="modules/k-diffusion" reattach=master
17:02:24-774427 DEBUG    Submodule: modules/k-diffusion / master
17:02:24-897645 DEBUG    Git detached head detected: folder="wiki" reattach=master
17:02:24-899640 DEBUG    Submodule: wiki / master
17:02:24-972613 DEBUG    Register paths
17:02:25-067343 DEBUG    Installed packages: 209
17:02:25-068608 DEBUG    Extensions all: ['Lora', 'sd-extension-chainner', 'sd-extension-system-info',
                         'sd-webui-agent-scheduler', 'sd-webui-controlnet', 'sdnext-modernui',
                         'stable-diffusion-webui-images-browser', 'stable-diffusion-webui-rembg']
17:02:25-260125 DEBUG    Running extension installer:
                         C:\ai\automatic\extensions-builtin\sd-extension-system-info\install.py
17:02:25-636886 DEBUG    Running extension installer:
                         C:\ai\automatic\extensions-builtin\sd-webui-agent-scheduler\install.py
17:02:26-014094 DEBUG    Running extension installer: C:\ai\automatic\extensions-builtin\sd-webui-controlnet\install.py
17:02:26-552536 DEBUG    Running extension installer:
                         C:\ai\automatic\extensions-builtin\stable-diffusion-webui-images-browser\install.py
17:02:26-932773 DEBUG    Running extension installer:
                         C:\ai\automatic\extensions-builtin\stable-diffusion-webui-rembg\install.py
17:02:27-303495 DEBUG    Extensions all: []
17:02:27-304492 INFO     Extensions enabled: ['Lora', 'sd-extension-chainner', 'sd-extension-system-info',
                         'sd-webui-agent-scheduler', 'sd-webui-controlnet', 'sdnext-modernui',
                         'stable-diffusion-webui-images-browser', 'stable-diffusion-webui-rembg']
17:02:27-305517 INFO     Verifying requirements
17:02:27-306517 DEBUG    Setup complete without errors: 1725458547
17:02:27-314465 DEBUG    Extension preload: {'extensions-builtin': 0.0, 'extensions': 0.0}
17:02:27-315462 DEBUG    Starting module: <module 'webui' from 'c:\\ai\\automatic\\webui.py'>
17:02:27-316460 INFO     Command line args: ['--medvram', '--debug'] medvram=True debug=True
17:02:27-317458 DEBUG    Env flags: ['SD_LOAD_DEBUG=true']
17:02:33-189459 INFO     Load packages: {'torch': '2.4.0+cu124', 'diffusers': '0.31.0.dev0', 'gradio': '3.43.2'}
17:02:34-227175 DEBUG    Read: file="config.json" json=35 bytes=1517 time=0.000
17:02:34-229169 DEBUG    Unknown settings: ['cross_attention_options']
17:02:34-231041 INFO     Engine: backend=Backend.DIFFUSERS compute=cuda device=cuda attention="Scaled-Dot-Product"
                         mode=no_grad
17:02:34-294317 INFO     Device: device=NVIDIA GeForce RTX 4080 n=1 arch=sm_90 cap=(8, 9) cuda=12.4 cudnn=90100
                         driver=560.81
17:02:34-296337 DEBUG    Read: file="html\reference.json" json=52 bytes=29118 time=0.000
17:02:34-675257 DEBUG    ONNX: version=1.19.0 provider=CUDAExecutionProvider, available=['AzureExecutionProvider',
                         'CPUExecutionProvider']
17:02:34-851643 DEBUG    Importing LDM
17:02:34-869313 DEBUG    Entering start sequence
17:02:34-872306 DEBUG    Initializing
17:02:34-897238 INFO     Available VAEs: path="models\VAE" items=0
17:02:34-899233 DEBUG    Available UNets: path="models\UNET" items=0
17:02:34-900612 DEBUG    Available T5s: path="models\T5" items=0
17:02:34-902402 INFO     Disabled extensions: ['sd-webui-controlnet', 'sdnext-modernui']
17:02:34-904118 DEBUG    Read: file="cache.json" json=2 bytes=10089 time=0.000
17:02:34-911099 DEBUG    Read: file="metadata.json" json=559 bytes=1861768 time=0.005
17:02:34-917083 DEBUG    Scanning diffusers cache: folder=models\Diffusers items=2 time=0.00
17:02:34-918215 INFO     Available models: path="models\Stable-diffusion" items=21 time=0.01
17:02:35-114252 DEBUG    Load extensions
17:02:35-159735 INFO     Extension: script='extensions-builtin\Lora\scripts\lora_script.py'
                         [2;36m17:02:35-156529[0m[2;36m [0m[34mINFO    [0m LoRA networks: [33mavailable[0m=[1;36m70[0m
                         [33mfolders[0m=[1;36m3[0m
17:02:35-533324 INFO     Extension: script='extensions-builtin\sd-webui-agent-scheduler\scripts\task_scheduler.py' Using
                         sqlite file: extensions-builtin\sd-webui-agent-scheduler\task_scheduler.sqlite3
17:02:35-729270 DEBUG    Extensions init time: 0.61 sd-webui-agent-scheduler=0.33
                         stable-diffusion-webui-images-browser=0.18
17:02:35-742236 DEBUG    Read: file="html/upscalers.json" json=4 bytes=2672 time=0.000
17:02:35-743234 DEBUG    Read: file="extensions-builtin\sd-extension-chainner\models.json" json=24 bytes=2719 time=0.000
17:02:35-745051 DEBUG    chaiNNer models: path="models\chaiNNer" defined=24 discovered=0 downloaded=8
17:02:35-747045 DEBUG    Upscaler type=ESRGAN folder="models\ESRGAN" model="1x-ITF-SkinDiffDetail-Lite-v1"
                         path="models\ESRGAN\1x-ITF-SkinDiffDetail-Lite-v1.pth"
17:02:35-748042 DEBUG    Upscaler type=ESRGAN folder="models\ESRGAN" model="4xNMKDSuperscale_4xNMKDSuperscale"
                         path="models\ESRGAN\4xNMKDSuperscale_4xNMKDSuperscale.pth"
17:02:35-750037 DEBUG    Upscaler type=ESRGAN folder="models\ESRGAN" model="4x_NMKD-Siax_200k"
                         path="models\ESRGAN\4x_NMKD-Siax_200k.pth"
17:02:35-753029 DEBUG    Load upscalers: total=56 downloaded=11 user=3 time=0.02 ['None', 'Lanczos', 'Nearest',
                         'ChaiNNer', 'AuraSR', 'ESRGAN', 'LDSR', 'RealESRGAN', 'SCUNet', 'SD', 'SwinIR']
17:02:35-769823 DEBUG    Load styles: folder="models\styles" items=288 time=0.02
17:02:35-772171 DEBUG    Creating UI
17:02:35-774007 DEBUG    UI themes available: type=Standard themes=12
17:02:35-774868 INFO     UI theme: type=Standard name="black-teal"
17:02:35-782847 DEBUG    UI theme: css="C:\ai\automatic\javascript\black-teal.css" base="sdnext.css" user="None"
17:02:35-785619 DEBUG    UI initialize: txt2img
17:02:35-843491 DEBUG    Networks: page='model' items=72 subfolders=2 tab=txt2img folders=['models\\Stable-diffusion',
                         'models\\Diffusers', 'models\\Reference'] list=0.04 thumb=0.01 desc=0.01 info=0.00 workers=4
                         sort=Default
17:02:35-852658 DEBUG    Networks: page='lora' items=70 subfolders=0 tab=txt2img folders=['models\\Lora',
                         'models\\LyCORIS'] list=0.04 thumb=0.01 desc=0.02 info=0.02 workers=4 sort=Default
17:02:35-884463 DEBUG    Networks: page='style' items=288 subfolders=1 tab=txt2img folders=['models\\styles', 'html']
                         list=0.04 thumb=0.00 desc=0.00 info=0.00 workers=4 sort=Default
17:02:35-889531 DEBUG    Networks: page='embedding' items=13 subfolders=0 tab=txt2img folders=['models\\embeddings']
                         list=0.03 thumb=0.01 desc=0.00 info=0.00 workers=4 sort=Default
17:02:35-891497 DEBUG    Networks: page='vae' items=0 subfolders=0 tab=txt2img folders=['models\\VAE'] list=0.00
                         thumb=0.00 desc=0.00 info=0.00 workers=4 sort=Default
17:02:35-967295 DEBUG    UI initialize: img2img
17:02:36-214436 DEBUG    UI initialize: control models=models\control
17:02:36-476429 DEBUG    Read: file="ui-config.json" json=0 bytes=2 time=0.000
17:02:36-575191 DEBUG    UI themes available: type=Standard themes=12
17:02:37-111806 DEBUG    Reading failed: C:\ai\automatic\html\extensions.json [Errno 2] No such file or directory:
                         'C:\\ai\\automatic\\html\\extensions.json'
17:02:37-113483 INFO     Extension list is empty: refresh required
17:02:37-696067 DEBUG    Extension list: processed=8 installed=8 enabled=6 disabled=2 visible=8 hidden=0
17:02:38-030172 DEBUG    Root paths: ['c:\\ai\\automatic']
17:02:38-105210 INFO     Local URL: http://127.0.0.1:7860/
17:02:38-106207 DEBUG    Gradio functions: registered=2364
17:02:38-107206 DEBUG    FastAPI middleware: ['Middleware', 'Middleware']
17:02:38-110196 DEBUG    Creating API
17:02:38-281876 INFO     [AgentScheduler] Task queue is empty
17:02:38-282874 INFO     [AgentScheduler] Registering APIs
17:02:38-402583 DEBUG    Scripts setup: ['IP Adapters:0.021', 'AnimateDiff:0.008', 'X/Y/Z Grid:0.01', 'Face:0.163']
17:02:38-404409 DEBUG    Model metadata: file="metadata.json" no changes
17:02:38-405437 DEBUG    Torch mode: deterministic=False
17:02:38-433707 INFO     Torch override VAE dtype: no-half set
17:02:38-435336 DEBUG    Desired Torch parameters: dtype=FP16 no-half=False no-half-vae=True upscast=False
17:02:38-435862 INFO     Setting Torch parameters: device=cuda dtype=torch.float16 vae=torch.float32 unet=torch.float16
                         context=no_grad fp16=True bf16=None optimization=Scaled-Dot-Product
17:02:38-438857 DEBUG    Model requested: fn=<lambda>
17:02:38-439855 INFO     Select: model="Diffusers\Disty0/FLUX.1-dev-qint4 [82811df42b]"
17:02:38-440851 DEBUG    Load model: existing=False
                         target=models\Diffusers\models--Disty0--FLUX.1-dev-qint4\snapshots\82811df42b556a1153b971d8375d
                         5170c306a6eb info=None
17:02:38-441849 DEBUG    Diffusers loading:
                         path="models\Diffusers\models--Disty0--FLUX.1-dev-qint4\snapshots\82811df42b556a1153b971d8375d5
                         170c306a6eb"
17:02:38-442847 INFO     Autodetect: model="FLUX" class=FluxPipeline
                         file="models\Diffusers\models--Disty0--FLUX.1-dev-qint4\snapshots\82811df42b556a1153b971d8375d5
                         170c306a6eb" size=0MB
17:02:38-446836 DEBUG    Loading FLUX: model="Diffusers\Disty0/FLUX.1-dev-qint4"
                         repo="Diffusers\Disty0/FLUX.1-dev-qint4" unet="None" t5="None" vae="None" quant=qint4
                         offload=model dtype=torch.float16
17:02:38-447833 TRACE    Loading FLUX: config={'low_cpu_mem_usage': True, 'torch_dtype': torch.float16,
                         'load_connected_pipeline': True, 'safety_checker': None, 'requires_safety_checker': False}
17:02:38-940479 TRACE    Loading FLUX: quantization
                         map="models\Diffusers\models--Disty0--FLUX.1-dev-qint4\snapshots\82811df42b556a1153b971d8375d51
                         70c306a6eb\transformer\quantization_map.json" repo="Diffusers\Disty0/FLUX.1-dev-qint4"
                         component="transformer"
17:02:38-942061 ERROR    Loading FLUX: Failed to load Quanto transformer: Repo id must use alphanumeric chars or '-',
                         '_', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is
                         96: 'Diffusers\Disty0/FLUX.1-dev-qint4'.
17:02:38-943709 ERROR    FLUX Quanto:: HFValidationError
╭───────────────────────────────────────── Traceback (most recent call last) ──────────────────────────────────────────╮
│ C:\ai\automatic\modules\model_flux.py:50 in load_flux_quanto                                                         │
│                                                                                                                      │
│    49 │   │   │   repo_id = checkpoint_info.name.replace('Diffusers/', '').replace('models--', '').replace('--', '/' │
│ ❱  50 │   │   │   quantization_map = hf_hub_download(repo_id, subfolder='transformer', filename='quantization_map.js │
│    51 │   │   with open(quantization_map, "r", encoding='utf8') as f:                                                │
│                                                                                                                      │
│ c:\ai\automatic\venv\Lib\site-packages\huggingface_hub\utils\_deprecation.py:101 in inner_f                          │
│                                                                                                                      │
│   100 │   │   │   │   warnings.warn(message, FutureWarning)                                                          │
│ ❱ 101 │   │   │   return f(*args, **kwargs)                                                                          │
│   102                                                                                                                │
│                                                                                                                      │
│ c:\ai\automatic\venv\Lib\site-packages\huggingface_hub\utils\_validators.py:106 in _inner_fn                         │
│                                                                                                                      │
│   105 │   │   │   if arg_name in ["repo_id", "from_id", "to_id"]:                                                    │
│ ❱ 106 │   │   │   │   validate_repo_id(arg_value)                                                                    │
│   107                                                                                                                │
│                                                                                                                      │
│ c:\ai\automatic\venv\Lib\site-packages\huggingface_hub\utils\_validators.py:160 in validate_repo_id                  │
│                                                                                                                      │
│   159 │   if not REPO_ID_REGEX.match(repo_id):                                                                       │
│ ❱ 160 │   │   raise HFValidationError(                                                                               │
│   161 │   │   │   "Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are"                          │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
HFValidationError: Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is 96: 'Diffusers\Disty0/FLUX.1-dev-qint4'.
17:02:38-990000 TRACE    Loading FLUX: quantization
                         map="models\Diffusers\models--Disty0--FLUX.1-dev-qint4\snapshots\82811df42b556a1153b971d8375d51
                         70c306a6eb\text_encoder_2\quantization_map.json" repo="Diffusers\Disty0/FLUX.1-dev-qint4"
                         component="text_encoder_2"
17:02:38-991000 ERROR    Loading FLUX: Failed to load Quanto text encoder: Repo id must use alphanumeric chars or '-',
                         '_', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is
                         96: 'Diffusers\Disty0/FLUX.1-dev-qint4'.
17:02:38-992994 ERROR    FLUX Quanto:: HFValidationError
╭───────────────────────────────────────── Traceback (most recent call last) ──────────────────────────────────────────╮
│ C:\ai\automatic\modules\model_flux.py:75 in load_flux_quanto                                                         │
│                                                                                                                      │
│    74 │   │   │   repo_id = checkpoint_info.name.replace('Diffusers/', '').replace('models--', '').replace('--', '/' │
│ ❱  75 │   │   │   quantization_map = hf_hub_download(repo_id, subfolder='text_encoder_2', filename='quantization_map │
│    76 │   │   with open(quantization_map, "r", encoding='utf8') as f:                                                │
│                                                                                                                      │
│ c:\ai\automatic\venv\Lib\site-packages\huggingface_hub\utils\_deprecation.py:101 in inner_f                          │
│                                                                                                                      │
│   100 │   │   │   │   warnings.warn(message, FutureWarning)                                                          │
│ ❱ 101 │   │   │   return f(*args, **kwargs)                                                                          │
│   102                                                                                                                │
│                                                                                                                      │
│ c:\ai\automatic\venv\Lib\site-packages\huggingface_hub\utils\_validators.py:106 in _inner_fn                         │
│                                                                                                                      │
│   105 │   │   │   if arg_name in ["repo_id", "from_id", "to_id"]:                                                    │
│ ❱ 106 │   │   │   │   validate_repo_id(arg_value)                                                                    │
│   107                                                                                                                │
│                                                                                                                      │
│ c:\ai\automatic\venv\Lib\site-packages\huggingface_hub\utils\_validators.py:160 in validate_repo_id                  │
│                                                                                                                      │
│   159 │   if not REPO_ID_REGEX.match(repo_id):                                                                       │
│ ❱ 160 │   │   raise HFValidationError(                                                                               │
│   161 │   │   │   "Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are"                          │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
HFValidationError: Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is 96: 'Diffusers\Disty0/FLUX.1-dev-qint4'.
17:02:39-015501 DEBUG    Loading FLUX: preloaded=[]
17:02:39-016498 ERROR    Diffusers Failed loading model:
                         models\Diffusers\models--Disty0--FLUX.1-dev-qint4\snapshots\82811df42b556a1153b971d8375d5170c30
                         6a6eb Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are forbidden, '-'
                         and '.' cannot start or end the name, max length is 96: 'Diffusers\Disty0/FLUX.1-dev-qint4'.
17:02:39-018493 ERROR    Load: HFValidationError
╭───────────────────────────────────────── Traceback (most recent call last) ──────────────────────────────────────────╮
│ C:\ai\automatic\modules\sd_models.py:1156 in load_diffuser                                                           │
│                                                                                                                      │
│   1155 │   │   │   │   │   from modules.model_flux import load_flux                                                  │
│ ❱ 1156 │   │   │   │   │   sd_model = load_flux(checkpoint_info, diffusers_load_config)                              │
│   1157 │   │   │   │   except Exception as e:                                                                        │
│                                                                                                                      │
│ C:\ai\automatic\modules\model_flux.py:241 in load_flux                                                               │
│                                                                                                                      │
│   240 │   shared.log.debug(f'Loading FLUX: preloaded={list(components)}')                                            │
│ ❱ 241 │   pipe = diffusers.FluxPipeline.from_pretrained(repo_id, cache_dir=shared.opts.diffusers_dir, **components,  │
│   242 │   return pipe                                                                                                │
│                                                                                                                      │
│ c:\ai\automatic\venv\Lib\site-packages\huggingface_hub\utils\_validators.py:114 in _inner_fn                         │
│                                                                                                                      │
│   113 │   │                                                                                                          │
│ ❱ 114 │   │   return fn(*args, **kwargs)                                                                             │
│   115                                                                                                                │
│                                                                                                                      │
│ c:\ai\automatic\venv\Lib\site-packages\diffusers\pipelines\pipeline_utils.py:706 in from_pretrained                  │
│                                                                                                                      │
│    705 │   │   │   │   )                                                                                             │
│ ❱  706 │   │   │   cached_folder = cls.download(                                                                     │
│    707 │   │   │   │   pretrained_model_name_or_path,                                                                │
│                                                                                                                      │
│ c:\ai\automatic\venv\Lib\site-packages\huggingface_hub\utils\_validators.py:114 in _inner_fn                         │
│                                                                                                                      │
│   113 │   │                                                                                                          │
│ ❱ 114 │   │   return fn(*args, **kwargs)                                                                             │
│   115                                                                                                                │
│                                                                                                                      │
│ c:\ai\automatic\venv\Lib\site-packages\diffusers\pipelines\pipeline_utils.py:1235 in download                        │
│                                                                                                                      │
│   1234 │   │   │   try:                                                                                              │
│ ❱ 1235 │   │   │   │   info = model_info(pretrained_model_name, token=token, revision=revision)                      │
│   1236 │   │   │   except (HTTPError, OfflineModeIsEnabled, requests.ConnectionError) as e:                          │
│                                                                                                                      │
│ c:\ai\automatic\venv\Lib\site-packages\huggingface_hub\utils\_validators.py:106 in _inner_fn                         │
│                                                                                                                      │
│   105 │   │   │   if arg_name in ["repo_id", "from_id", "to_id"]:                                                    │
│ ❱ 106 │   │   │   │   validate_repo_id(arg_value)                                                                    │
│   107                                                                                                                │
│                                                                                                                      │
│ c:\ai\automatic\venv\Lib\site-packages\huggingface_hub\utils\_validators.py:160 in validate_repo_id                  │
│                                                                                                                      │
│   159 │   if not REPO_ID_REGEX.match(repo_id):                                                                       │
│ ❱ 160 │   │   raise HFValidationError(                                                                               │
│   161 │   │   │   "Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are"                          │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
HFValidationError: Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is 96: 'Diffusers\Disty0/FLUX.1-dev-qint4'.
17:02:39-260847 DEBUG    Script callback init time: image_browser.py:ui_tabs=0.40 system-info.py:app_started=0.06
                         task_scheduler.py:app_started=0.14
17:02:39-262165 INFO     Startup time: 11.94 torch=4.17 gradio=1.29 diffusers=0.41 libraries=1.66 extensions=0.61
                         face-restore=0.20 ui-en=0.21 ui-txt2img=0.06 ui-img2img=0.21 ui-control=0.11 ui-settings=0.23
                         ui-extensions=1.02 ui-defaults=0.26 launch=0.13 api=0.09 app-started=0.20 checkpoint=0.86
17:02:39-264168 DEBUG    Save: file="config.json" json=35 bytes=1470 time=0.004
17:02:39-266162 DEBUG    Unused settings: ['cross_attention_options']

ah, need to handle windows path, my bad - try update and all again?

Not working, but different errors

c:\ai\automatic>.\webui.bat --medvram --debug
Using VENV: c:\ai\automatic\venv
17:59:23-868420 INFO     Starting SD.Next
17:59:23-872025 INFO     Logger: file="c:\ai\automatic\sdnext.log" level=DEBUG size=65 mode=create
17:59:23-873792 INFO     Python version=3.11.9 platform=Windows bin="c:\ai\automatic\venv\Scripts\python.exe"
                         venv="c:\ai\automatic\venv"
17:59:24-077348 INFO     Version: app=sd.next updated=2024-09-04 hash=ce94b5a9 branch=dev
                         url=https://github.com/vladmandic/automatic/tree/dev ui=dev
17:59:24-881314 INFO     Latest published version: bab17a0b4f91b41c885f10262ef8c8e70ba72faa 2024-08-31T20:57:34Z
17:59:24-895164 INFO     Platform: arch=AMD64 cpu=Intel64 Family 6 Model 165 Stepping 5, GenuineIntel system=Windows
                         release=Windows-10-10.0.22631-SP0 python=3.11.9
17:59:24-896162 DEBUG    Setting environment tuning
17:59:24-898157 INFO     HF cache folder: C:\Users\sebas\.cache\huggingface\hub
17:59:24-898157 DEBUG    Torch allocator: "garbage_collection_threshold:0.80,max_split_size_mb:512"
17:59:24-909127 DEBUG    Torch overrides: cuda=False rocm=False ipex=False diml=False openvino=False
17:59:24-910125 DEBUG    Torch allowed: cuda=True rocm=True ipex=True diml=True openvino=True
17:59:24-920098 INFO     nVidia CUDA toolkit detected: nvidia-smi present
17:59:25-002448 WARNING  Modified files: ['models/Reference/playgroundai--playground-v2-1024px-aesthetic.jpg']
17:59:25-097194 INFO     Verifying requirements
17:59:25-100893 INFO     Verifying packages
17:59:25-143779 DEBUG    Repository update time: Wed Sep  4 17:39:01 2024
17:59:25-145746 INFO     Startup: standard
17:59:25-146125 INFO     Verifying submodules
17:59:28-032578 DEBUG    Git detached head detected: folder="extensions-builtin/sd-extension-chainner" reattach=main
17:59:28-032983 DEBUG    Submodule: extensions-builtin/sd-extension-chainner / main
17:59:28-161529 DEBUG    Git detached head detected: folder="extensions-builtin/sd-extension-system-info" reattach=main
17:59:28-162526 DEBUG    Submodule: extensions-builtin/sd-extension-system-info / main
17:59:28-289859 DEBUG    Git detached head detected: folder="extensions-builtin/sd-webui-agent-scheduler" reattach=main
17:59:28-290852 DEBUG    Submodule: extensions-builtin/sd-webui-agent-scheduler / main
17:59:28-474036 DEBUG    Git detached head detected: folder="extensions-builtin/sdnext-modernui" reattach=dev
17:59:28-475033 DEBUG    Submodule: extensions-builtin/sdnext-modernui / dev
17:59:28-622991 DEBUG    Git detached head detected: folder="extensions-builtin/stable-diffusion-webui-rembg"
                         reattach=master
17:59:28-624959 DEBUG    Submodule: extensions-builtin/stable-diffusion-webui-rembg / master
17:59:28-752795 DEBUG    Git detached head detected: folder="modules/k-diffusion" reattach=master
17:59:28-753792 DEBUG    Submodule: modules/k-diffusion / master
17:59:28-883211 DEBUG    Git detached head detected: folder="wiki" reattach=master
17:59:28-885206 DEBUG    Submodule: wiki / master
17:59:28-959796 DEBUG    Register paths
17:59:29-058532 DEBUG    Installed packages: 209
17:59:29-060598 DEBUG    Extensions all: ['Lora', 'sd-extension-chainner', 'sd-extension-system-info',
                         'sd-webui-agent-scheduler', 'sd-webui-controlnet', 'sdnext-modernui',
                         'stable-diffusion-webui-images-browser', 'stable-diffusion-webui-rembg']
17:59:29-242114 DEBUG    Running extension installer:
                         C:\ai\automatic\extensions-builtin\sd-extension-system-info\install.py
17:59:29-618762 DEBUG    Running extension installer:
                         C:\ai\automatic\extensions-builtin\sd-webui-agent-scheduler\install.py
17:59:29-994073 DEBUG    Running extension installer: C:\ai\automatic\extensions-builtin\sd-webui-controlnet\install.py
17:59:30-538475 DEBUG    Running extension installer:
                         C:\ai\automatic\extensions-builtin\stable-diffusion-webui-images-browser\install.py
17:59:30-915614 DEBUG    Running extension installer:
                         C:\ai\automatic\extensions-builtin\stable-diffusion-webui-rembg\install.py
17:59:31-286851 DEBUG    Extensions all: []
17:59:31-288629 INFO     Extensions enabled: ['Lora', 'sd-extension-chainner', 'sd-extension-system-info',
                         'sd-webui-agent-scheduler', 'sd-webui-controlnet', 'sdnext-modernui',
                         'stable-diffusion-webui-images-browser', 'stable-diffusion-webui-rembg']
17:59:31-290132 INFO     Verifying requirements
17:59:31-290132 DEBUG    Setup complete without errors: 1725461971
17:59:31-298110 DEBUG    Extension preload: {'extensions-builtin': 0.0, 'extensions': 0.0}
17:59:31-299108 DEBUG    Starting module: <module 'webui' from 'c:\\ai\\automatic\\webui.py'>
17:59:31-300106 INFO     Command line args: ['--medvram', '--debug'] medvram=True debug=True
17:59:31-301103 DEBUG    Env flags: ['SD_LOAD_DEBUG=true']
17:59:37-111449 INFO     Load packages: {'torch': '2.4.0+cu124', 'diffusers': '0.31.0.dev0', 'gradio': '3.43.2'}
17:59:38-150448 DEBUG    Read: file="config.json" json=35 bytes=1517 time=0.000
17:59:38-151446 DEBUG    Unknown settings: ['cross_attention_options']
17:59:38-154438 INFO     Engine: backend=Backend.DIFFUSERS compute=cuda device=cuda attention="Scaled-Dot-Product"
                         mode=no_grad
17:59:38-212319 INFO     Device: device=NVIDIA GeForce RTX 4080 n=1 arch=sm_90 cap=(8, 9) cuda=12.4 cudnn=90100
                         driver=560.81
17:59:38-214321 DEBUG    Read: file="html\reference.json" json=52 bytes=29118 time=0.000
17:59:38-591437 DEBUG    ONNX: version=1.19.0 provider=CUDAExecutionProvider, available=['AzureExecutionProvider',
                         'CPUExecutionProvider']
17:59:38-766639 DEBUG    Importing LDM
17:59:38-784209 DEBUG    Entering start sequence
17:59:38-786424 DEBUG    Initializing
17:59:38-812422 INFO     Available VAEs: path="models\VAE" items=0
17:59:38-814416 DEBUG    Available UNets: path="models\UNET" items=0
17:59:38-815612 DEBUG    Available T5s: path="models\T5" items=0
17:59:38-816639 INFO     Disabled extensions: ['sd-webui-controlnet', 'sdnext-modernui']
17:59:38-818606 DEBUG    Read: file="cache.json" json=2 bytes=10089 time=0.000
17:59:38-826585 DEBUG    Read: file="metadata.json" json=559 bytes=1861768 time=0.006
17:59:38-831254 DEBUG    Scanning diffusers cache: folder=models\Diffusers items=2 time=0.00
17:59:38-833117 INFO     Available models: path="models\Stable-diffusion" items=21 time=0.01
17:59:39-029780 DEBUG    Load extensions
17:59:39-077641 INFO     Extension: script='extensions-builtin\Lora\scripts\lora_script.py'
                         [2;36m17:59:39-073652[0m[2;36m [0m[34mINFO    [0m LoRA networks: [33mavailable[0m=[1;36m70[0m
                         [33mfolders[0m=[1;36m2[0m
17:59:39-455871 INFO     Extension: script='extensions-builtin\sd-webui-agent-scheduler\scripts\task_scheduler.py' Using
                         sqlite file: extensions-builtin\sd-webui-agent-scheduler\task_scheduler.sqlite3
17:59:39-653674 DEBUG    Extensions init time: 0.62 sd-webui-agent-scheduler=0.33
                         stable-diffusion-webui-images-browser=0.18
17:59:39-666640 DEBUG    Read: file="html/upscalers.json" json=4 bytes=2672 time=0.000
17:59:39-667607 DEBUG    Read: file="extensions-builtin\sd-extension-chainner\models.json" json=24 bytes=2719 time=0.000
17:59:39-670600 DEBUG    chaiNNer models: path="models\chaiNNer" defined=24 discovered=0 downloaded=8
17:59:39-672594 DEBUG    Upscaler type=ESRGAN folder="models\ESRGAN" model="1x-ITF-SkinDiffDetail-Lite-v1"
                         path="models\ESRGAN\1x-ITF-SkinDiffDetail-Lite-v1.pth"
17:59:39-673592 DEBUG    Upscaler type=ESRGAN folder="models\ESRGAN" model="4xNMKDSuperscale_4xNMKDSuperscale"
                         path="models\ESRGAN\4xNMKDSuperscale_4xNMKDSuperscale.pth"
17:59:39-674589 DEBUG    Upscaler type=ESRGAN folder="models\ESRGAN" model="4x_NMKD-Siax_200k"
                         path="models\ESRGAN\4x_NMKD-Siax_200k.pth"
17:59:39-677581 DEBUG    Load upscalers: total=56 downloaded=11 user=3 time=0.02 ['None', 'Lanczos', 'Nearest',
                         'ChaiNNer', 'AuraSR', 'ESRGAN', 'LDSR', 'RealESRGAN', 'SCUNet', 'SD', 'SwinIR']
17:59:39-695532 DEBUG    Load styles: folder="models\styles" items=288 time=0.02
17:59:39-698527 DEBUG    Creating UI
17:59:39-699524 DEBUG    UI themes available: type=Standard themes=12
17:59:39-701517 INFO     UI theme: type=Standard name="black-teal"
17:59:39-708498 DEBUG    UI theme: css="C:\ai\automatic\javascript\black-teal.css" base="sdnext.css" user="None"
17:59:39-710492 DEBUG    UI initialize: txt2img
17:59:39-769917 DEBUG    Networks: page='model' items=72 subfolders=2 tab=txt2img folders=['models\\Stable-diffusion',
                         'models\\Diffusers', 'models\\Reference'] list=0.04 thumb=0.01 desc=0.00 info=0.00 workers=4
                         sort=Default
17:59:39-777896 DEBUG    Networks: page='lora' items=70 subfolders=0 tab=txt2img folders=['models\\Lora',
                         'models\\LyCORIS'] list=0.04 thumb=0.01 desc=0.02 info=0.02 workers=4 sort=Default
17:59:39-809007 DEBUG    Networks: page='style' items=288 subfolders=1 tab=txt2img folders=['models\\styles', 'html']
                         list=0.04 thumb=0.00 desc=0.00 info=0.00 workers=4 sort=Default
17:59:39-813993 DEBUG    Networks: page='embedding' items=13 subfolders=0 tab=txt2img folders=['models\\embeddings']
                         list=0.03 thumb=0.01 desc=0.00 info=0.00 workers=4 sort=Default
17:59:39-816411 DEBUG    Networks: page='vae' items=0 subfolders=0 tab=txt2img folders=['models\\VAE'] list=0.00
                         thumb=0.00 desc=0.00 info=0.00 workers=4 sort=Default
17:59:39-892210 DEBUG    UI initialize: img2img
17:59:40-135754 DEBUG    UI initialize: control models=models\control
17:59:40-400507 DEBUG    Read: file="ui-config.json" json=0 bytes=2 time=0.001
17:59:40-498271 DEBUG    UI themes available: type=Standard themes=12
17:59:41-034803 DEBUG    Reading failed: C:\ai\automatic\html\extensions.json [Errno 2] No such file or directory:
                         'C:\\ai\\automatic\\html\\extensions.json'
17:59:41-037061 INFO     Extension list is empty: refresh required
17:59:41-621196 DEBUG    Extension list: processed=8 installed=8 enabled=6 disabled=2 visible=8 hidden=0
17:59:41-949475 DEBUG    Root paths: ['c:\\ai\\automatic']
17:59:42-025795 INFO     Local URL: http://127.0.0.1:7860/
17:59:42-026795 DEBUG    Gradio functions: registered=2363
17:59:42-028759 DEBUG    FastAPI middleware: ['Middleware', 'Middleware']
17:59:42-031752 DEBUG    Creating API
17:59:42-198334 INFO     [AgentScheduler] Task queue is empty
17:59:42-200302 INFO     [AgentScheduler] Registering APIs
17:59:42-316990 DEBUG    Scripts setup: ['IP Adapters:0.021', 'AnimateDiff:0.007', 'X/Y/Z Grid:0.011', 'Face:0.012']
17:59:42-318777 DEBUG    Model metadata: file="metadata.json" no changes
17:59:42-320135 DEBUG    Torch mode: deterministic=False
17:59:42-348090 INFO     Torch override VAE dtype: no-half set
17:59:42-349087 DEBUG    Desired Torch parameters: dtype=FP16 no-half=False no-half-vae=True upscast=False
17:59:42-349776 INFO     Setting Torch parameters: device=cuda dtype=torch.float16 vae=torch.float32 unet=torch.float16
                         context=no_grad fp16=True bf16=None optimization=Scaled-Dot-Product
17:59:42-351773 DEBUG    Model requested: fn=<lambda>
17:59:42-352772 INFO     Select: model="Diffusers\Disty0/FLUX.1-dev-qint4 [82811df42b]"
17:59:42-354766 DEBUG    Load model: existing=False
                         target=models\Diffusers\models--Disty0--FLUX.1-dev-qint4\snapshots\82811df42b556a1153b971d8375d
                         5170c306a6eb info=None
17:59:42-355764 DEBUG    Diffusers loading:
                         path="models\Diffusers\models--Disty0--FLUX.1-dev-qint4\snapshots\82811df42b556a1153b971d8375d5
                         170c306a6eb"
17:59:42-356761 INFO     Autodetect: model="FLUX" class=FluxPipeline
                         file="models\Diffusers\models--Disty0--FLUX.1-dev-qint4\snapshots\82811df42b556a1153b971d8375d5
                         170c306a6eb" size=0MB
17:59:42-359753 DEBUG    Loading FLUX: model="Diffusers\Disty0/FLUX.1-dev-qint4" repo="Disty0/FLUX.1-dev-qint4"
                         unet="None" t5="None" vae="None" quant=qint4 offload=model dtype=torch.float16
17:59:42-361748 TRACE    Loading FLUX: config={'low_cpu_mem_usage': True, 'torch_dtype': torch.float16,
                         'load_connected_pipeline': True, 'safety_checker': None, 'requires_safety_checker': False}
17:59:42-855418 TRACE    Loading FLUX: quantization
                         map="models\Diffusers\models--Disty0--FLUX.1-dev-qint4\snapshots\82811df42b556a1153b971d8375d51
                         70c306a6eb\transformer\quantization_map.json" repo="Diffusers\Disty0/FLUX.1-dev-qint4"
                         component="transformer"
17:59:42-857413 ERROR    Loading FLUX: Failed to load Quanto transformer: hf_hub_download() got an unexpected keyword
                         argument 'low_cpu_mem_usage'
17:59:42-857845 ERROR    FLUX Quanto:: TypeError
╭───────────────────────────────────────── Traceback (most recent call last) ──────────────────────────────────────────╮
│ C:\ai\automatic\modules\model_flux.py:50 in load_flux_quanto                                                         │
│                                                                                                                      │
│    49 │   │   │   repo_id = checkpoint_info.name.replace('Diffusers/', '').replace('Diffusers\\', '').replace('model │
│ ❱  50 │   │   │   quantization_map = hf_hub_download(repo_id, subfolder='transformer', filename='quantization_map.js │
│    51 │   │   with open(quantization_map, "r", encoding='utf8') as f:                                                │
│                                                                                                                      │
│ c:\ai\automatic\venv\Lib\site-packages\huggingface_hub\utils\_deprecation.py:101 in inner_f                          │
│                                                                                                                      │
│   100 │   │   │   │   warnings.warn(message, FutureWarning)                                                          │
│ ❱ 101 │   │   │   return f(*args, **kwargs)                                                                          │
│   102                                                                                                                │
│                                                                                                                      │
│ c:\ai\automatic\venv\Lib\site-packages\huggingface_hub\utils\_validators.py:114 in _inner_fn                         │
│                                                                                                                      │
│   113 │   │                                                                                                          │
│ ❱ 114 │   │   return fn(*args, **kwargs)                                                                             │
│   115                                                                                                                │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
TypeError: hf_hub_download() got an unexpected keyword argument 'low_cpu_mem_usage'
17:59:42-899735 TRACE    Loading FLUX: quantization
                         map="models\Diffusers\models--Disty0--FLUX.1-dev-qint4\snapshots\82811df42b556a1153b971d8375d51
                         70c306a6eb\text_encoder_2\quantization_map.json" repo="Diffusers\Disty0/FLUX.1-dev-qint4"
                         component="text_encoder_2"
17:59:42-901731 ERROR    Loading FLUX: Failed to load Quanto text encoder: hf_hub_download() got an unexpected keyword
                         argument 'low_cpu_mem_usage'
17:59:42-902727 ERROR    FLUX Quanto:: TypeError
╭───────────────────────────────────────── Traceback (most recent call last) ──────────────────────────────────────────╮
│ C:\ai\automatic\modules\model_flux.py:75 in load_flux_quanto                                                         │
│                                                                                                                      │
│    74 │   │   │   repo_id = checkpoint_info.name.replace('Diffusers/', '').replace('Diffusers\\', '').replace('model │
│ ❱  75 │   │   │   quantization_map = hf_hub_download(repo_id, subfolder='text_encoder_2', filename='quantization_map │
│    76 │   │   with open(quantization_map, "r", encoding='utf8') as f:                                                │
│                                                                                                                      │
│ c:\ai\automatic\venv\Lib\site-packages\huggingface_hub\utils\_deprecation.py:101 in inner_f                          │
│                                                                                                                      │
│   100 │   │   │   │   warnings.warn(message, FutureWarning)                                                          │
│ ❱ 101 │   │   │   return f(*args, **kwargs)                                                                          │
│   102                                                                                                                │
│                                                                                                                      │
│ c:\ai\automatic\venv\Lib\site-packages\huggingface_hub\utils\_validators.py:114 in _inner_fn                         │
│                                                                                                                      │
│   113 │   │                                                                                                          │
│ ❱ 114 │   │   return fn(*args, **kwargs)                                                                             │
│   115                                                                                                                │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
TypeError: hf_hub_download() got an unexpected keyword argument 'low_cpu_mem_usage'
17:59:42-922737 DEBUG    Loading FLUX: preloaded=[]
Loading pipeline components...  14% ━━━━━━━╺━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1/7  [ 0:00:00 < -:--:-- , ? C/s ]
17:59:43-922282 ERROR    Diffusers Failed loading model:
                         models\Diffusers\models--Disty0--FLUX.1-dev-qint4\snapshots\82811df42b556a1153b971d8375d5170c30
                         6a6eb Cannot load <class
                         'diffusers.models.transformers.transformer_flux.FluxTransformer2DModel'> from
                         models\Diffusers\models--Disty0--FLUX.1-dev-qint4\snapshots\82811df42b556a1153b971d8375d5170c30
                         6a6eb\transformer because the following keys are missing:
                          transformer_blocks.2.attn.to_k.weight, transformer_blocks.8.norm1.linear.weight,
                         transformer_blocks.5.attn.add_v_proj.weight, transformer_blocks.16.ff_context.net.2.weight,
                         transformer_blocks.0.attn.to_add_out.weight, transformer_blocks.8.attn.to_k.weight,
                         transformer_blocks.5.norm1_context.linear.weight, transformer_blocks.13.attn.add_k_proj.weight,
                         transformer_blocks.0.ff.net.2.weight, single_transformer_blocks.23.norm.linear.weight,
                         single_transformer_blocks.24.norm.linear.weight, transformer_blocks.8.attn.to_q.weight,
                         single_transformer_blocks.28.attn.to_q.weight, single_transformer_blocks.20.norm.linear.weight,
                         single_transformer_blocks.36.proj_out.weight, transformer_blocks.11.attn.add_q_proj.weight,
                         transformer_blocks.12.attn.to_k.weight, single_transformer_blocks.6.proj_mlp.weight,
                         single_transformer_blocks.27.proj_out.weight, transformer_blocks.1.attn.add_k_proj.weight,
                         single_transformer_blocks.2.norm.linear.weight, transformer_blocks.4.attn.add_q_proj.weight,
                         transformer_blocks.12.attn.to_out.0.weight, single_transformer_blocks.32.proj_out.weight,
                         single_transformer_blocks.3.norm.linear.weight, transformer_blocks.5.ff_context.net.2.weight,
                         transformer_blocks.9.attn.to_k.weight, transformer_blocks.12.ff.net.2.weight,
                         single_transformer_blocks.0.attn.to_q.weight,
                         time_text_embed.timestep_embedder.linear_1.weight,
                         transformer_blocks.12.ff_context.net.2.weight, transformer_blocks.5.ff.net.0.proj.weight,
                         single_transformer_blocks.21.attn.to_k.weight, transformer_blocks.0.ff_context.net.2.weight,
                         single_transformer_blocks.23.attn.to_v.weight, transformer_blocks.5.attn.to_k.weight,
                         transformer_blocks.9.ff.net.0.proj.weight, single_transformer_blocks.35.attn.to_v.weight,
                         single_transformer_blocks.25.attn.to_q.weight, transformer_blocks.8.attn.add_q_proj.weight,
                         single_transformer_blocks.0.attn.to_k.weight, transformer_blocks.18.attn.to_q.weight,
                         single_transformer_blocks.2.proj_out.weight, single_transformer_blocks.24.proj_out.weight,
                         transformer_blocks.5.attn.to_out.0.weight, single_transformer_blocks.8.attn.to_k.weight,
                         transformer_blocks.18.attn.add_k_proj.weight, single_transformer_blocks.22.proj_mlp.weight,
                         transformer_blocks.16.ff_context.net.0.proj.weight, transformer_blocks.17.attn.to_k.weight,
                         single_transformer_blocks.18.proj_mlp.weight, transformer_blocks.15.ff.net.2.weight,
                         transformer_blocks.7.ff_context.net.2.weight, single_transformer_blocks.36.attn.to_q.weight,
                         transformer_blocks.13.attn.to_v.weight, single_transformer_blocks.34.attn.to_k.weight,
                         single_transformer_blocks.12.attn.to_v.weight, single_transformer_blocks.22.norm.linear.weight,
                         transformer_blocks.10.ff_context.net.2.weight, transformer_blocks.0.attn.add_k_proj.weight,
                         transformer_blocks.9.attn.to_add_out.weight, single_transformer_blocks.26.proj_mlp.weight,
                         transformer_blocks.6.attn.to_out.0.weight, single_transformer_blocks.13.norm.linear.weight,
                         single_transformer_blocks.11.attn.to_k.weight, transformer_blocks.1.attn.add_v_proj.weight,
                         transformer_blocks.1.attn.to_q.weight, transformer_blocks.15.ff_context.net.2.weight,
                         transformer_blocks.15.attn.to_add_out.weight, single_transformer_blocks.0.proj_out.weight,
                         transformer_blocks.4.attn.add_k_proj.weight, transformer_blocks.3.norm1_context.linear.weight,
                         single_transformer_blocks.3.proj_mlp.weight, single_transformer_blocks.17.attn.to_k.weight,
                         transformer_blocks.5.attn.to_v.weight, single_transformer_blocks.5.norm.linear.weight,
                         single_transformer_blocks.10.norm.linear.weight, single_transformer_blocks.0.proj_mlp.weight,
                         transformer_blocks.9.ff_context.net.0.proj.weight, transformer_blocks.13.ff.net.0.proj.weight,
                         single_transformer_blocks.8.proj_out.weight, transformer_blocks.0.attn.to_q.weight,
                         transformer_blocks.14.ff.net.2.weight, transformer_blocks.1.attn.add_q_proj.weight,
                         transformer_blocks.16.ff.net.0.proj.weight, transformer_blocks.18.norm1.linear.weight,
                         transformer_blocks.1.ff.net.0.proj.weight, transformer_blocks.3.attn.add_k_proj.weight,
                         transformer_blocks.14.attn.to_q.weight, transformer_blocks.9.attn.add_v_proj.weight,
                         single_transformer_blocks.36.attn.to_k.weight, single_transformer_blocks.3.attn.to_k.weight,
                         transformer_blocks.7.attn.add_v_proj.weight, single_transformer_blocks.7.attn.to_q.weight,
                         transformer_blocks.17.ff.net.0.proj.weight, transformer_blocks.4.attn.to_out.0.weight,
                         transformer_blocks.4.attn.to_q.weight, single_transformer_blocks.30.attn.to_q.weight,
                         transformer_blocks.5.ff_context.net.0.proj.weight, transformer_blocks.12.norm1.linear.weight,
                         transformer_blocks.14.attn.to_add_out.weight, single_transformer_blocks.2.attn.to_q.weight,
                         transformer_blocks.6.attn.to_k.weight, transformer_blocks.11.ff_context.net.2.weight,
                         transformer_blocks.16.attn.to_q.weight, transformer_blocks.8.ff.net.2.weight,
                         single_transformer_blocks.23.attn.to_q.weight, norm_out.linear.weight,
                         single_transformer_blocks.7.proj_mlp.weight, transformer_blocks.10.attn.add_v_proj.weight,
                         transformer_blocks.16.attn.to_out.0.weight, single_transformer_blocks.1.attn.to_v.weight,
                         single_transformer_blocks.33.attn.to_q.weight, transformer_blocks.11.attn.to_v.weight,
                         single_transformer_blocks.26.attn.to_q.weight, single_transformer_blocks.9.attn.to_q.weight,
                         transformer_blocks.12.ff_context.net.0.proj.weight,
                         transformer_blocks.5.attn.add_k_proj.weight, transformer_blocks.18.attn.to_out.0.weight,
                         transformer_blocks.6.ff_context.net.2.weight, transformer_blocks.12.attn.add_k_proj.weight,
                         transformer_blocks.15.attn.add_v_proj.weight, single_transformer_blocks.26.attn.to_v.weight,
                         time_text_embed.text_embedder.linear_1.weight,
                         transformer_blocks.18.norm1_context.linear.weight, transformer_blocks.14.attn.to_out.0.weight,
                         single_transformer_blocks.6.attn.to_q.weight, transformer_blocks.17.attn.to_add_out.weight,
                         transformer_blocks.10.attn.to_q.weight, transformer_blocks.17.norm1_context.linear.weight,
                         transformer_blocks.3.ff_context.net.0.proj.weight,
                         single_transformer_blocks.15.proj_out.weight, transformer_blocks.8.attn.to_add_out.weight,
                         transformer_blocks.10.ff_context.net.0.proj.weight,
                         single_transformer_blocks.24.attn.to_k.weight, transformer_blocks.13.ff_context.net.2.weight,
                         transformer_blocks.16.attn.to_v.weight, transformer_blocks.10.attn.add_k_proj.weight,
                         transformer_blocks.7.attn.add_q_proj.weight, single_transformer_blocks.26.norm.linear.weight,
                         transformer_blocks.11.ff_context.net.0.proj.weight,
                         single_transformer_blocks.13.attn.to_v.weight, single_transformer_blocks.16.proj_mlp.weight,
                         single_transformer_blocks.13.proj_mlp.weight, transformer_blocks.14.norm1.linear.weight,
                         single_transformer_blocks.1.norm.linear.weight, single_transformer_blocks.1.proj_mlp.weight,
                         single_transformer_blocks.16.norm.linear.weight, transformer_blocks.17.attn.to_out.0.weight,
                         transformer_blocks.5.attn.to_add_out.weight, transformer_blocks.13.ff.net.2.weight,
                         transformer_blocks.12.ff.net.0.proj.weight, transformer_blocks.3.attn.to_out.0.weight,
                         transformer_blocks.15.attn.to_out.0.weight, transformer_blocks.14.ff_context.net.2.weight,
                         transformer_blocks.15.attn.add_k_proj.weight, transformer_blocks.17.ff_context.net.2.weight,
                         single_transformer_blocks.8.attn.to_v.weight,
                         time_text_embed.timestep_embedder.linear_2.weight,
                         single_transformer_blocks.10.attn.to_q.weight, single_transformer_blocks.12.norm.linear.weight,
                         transformer_blocks.4.attn.to_v.weight, single_transformer_blocks.24.attn.to_q.weight,
                         transformer_blocks.0.norm1_context.linear.weight, transformer_blocks.17.norm1.linear.weight,
                         transformer_blocks.18.attn.to_add_out.weight, single_transformer_blocks.24.attn.to_v.weight,
                         single_transformer_blocks.25.proj_out.weight,
                         transformer_blocks.12.norm1_context.linear.weight,
                         single_transformer_blocks.10.attn.to_k.weight, single_transformer_blocks.15.proj_mlp.weight,
                         single_transformer_blocks.31.attn.to_k.weight, transformer_blocks.5.attn.add_q_proj.weight,
                         transformer_blocks.18.attn.to_k.weight, transformer_blocks.3.ff.net.0.proj.weight,
                         single_transformer_blocks.20.proj_out.weight,
                         time_text_embed.guidance_embedder.linear_2.weight,
                         transformer_blocks.18.attn.add_v_proj.weight, single_transformer_blocks.21.norm.linear.weight,
                         transformer_blocks.17.attn.add_k_proj.weight, transformer_blocks.17.attn.to_v.weight,
                         transformer_blocks.9.ff.net.2.weight, transformer_blocks.17.ff.net.2.weight,
                         single_transformer_blocks.14.proj_mlp.weight, x_embedder.weight,
                         single_transformer_blocks.30.attn.to_k.weight, transformer_blocks.0.attn.add_v_proj.weight,
                         single_transformer_blocks.31.proj_mlp.weight, single_transformer_blocks.32.proj_mlp.weight,
                         transformer_blocks.14.attn.add_k_proj.weight, single_transformer_blocks.16.attn.to_q.weight,
                         single_transformer_blocks.27.attn.to_q.weight, transformer_blocks.15.attn.to_k.weight,
                         single_transformer_blocks.10.proj_out.weight, transformer_blocks.1.ff.net.2.weight,
                         transformer_blocks.7.attn.to_add_out.weight, single_transformer_blocks.8.proj_mlp.weight,
                         single_transformer_blocks.5.attn.to_v.weight, transformer_blocks.14.attn.add_q_proj.weight,
                         transformer_blocks.11.norm1.linear.weight, single_transformer_blocks.31.proj_out.weight,
                         transformer_blocks.2.attn.to_q.weight, transformer_blocks.16.attn.add_k_proj.weight,
                         transformer_blocks.8.ff.net.0.proj.weight, single_transformer_blocks.22.attn.to_v.weight,
                         single_transformer_blocks.17.attn.to_q.weight, transformer_blocks.18.ff.net.0.proj.weight,
                         transformer_blocks.3.attn.to_add_out.weight, single_transformer_blocks.16.attn.to_k.weight,
                         transformer_blocks.17.attn.add_v_proj.weight, single_transformer_blocks.1.attn.to_k.weight,
                         single_transformer_blocks.29.proj_out.weight, transformer_blocks.3.attn.to_k.weight,
                         single_transformer_blocks.21.attn.to_q.weight,
                         transformer_blocks.15.norm1_context.linear.weight,
                         transformer_blocks.13.ff_context.net.0.proj.weight,
                         transformer_blocks.1.norm1_context.linear.weight, transformer_blocks.2.attn.add_q_proj.weight,
                         transformer_blocks.6.norm1.linear.weight, single_transformer_blocks.31.attn.to_v.weight,
                         single_transformer_blocks.17.norm.linear.weight, transformer_blocks.15.norm1.linear.weight,
                         transformer_blocks.15.ff_context.net.0.proj.weight,
                         single_transformer_blocks.37.proj_mlp.weight,
                         transformer_blocks.0.ff_context.net.0.proj.weight, transformer_blocks.12.attn.to_q.weight,
                         single_transformer_blocks.24.proj_mlp.weight, single_transformer_blocks.5.proj_mlp.weight,
                         single_transformer_blocks.35.proj_mlp.weight, single_transformer_blocks.20.attn.to_k.weight,
                         transformer_blocks.13.attn.to_out.0.weight, transformer_blocks.7.norm1.linear.weight,
                         transformer_blocks.3.ff_context.net.2.weight, single_transformer_blocks.22.attn.to_q.weight,
                         transformer_blocks.4.ff_context.net.2.weight, transformer_blocks.17.attn.to_q.weight,
                         transformer_blocks.7.attn.to_out.0.weight, single_transformer_blocks.27.attn.to_k.weight,
                         single_transformer_blocks.5.attn.to_k.weight, transformer_blocks.7.ff.net.2.weight,
                         single_transformer_blocks.14.attn.to_k.weight, transformer_blocks.4.ff.net.0.proj.weight,
                         single_transformer_blocks.29.attn.to_v.weight, transformer_blocks.3.norm1.linear.weight,
                         transformer_blocks.0.ff.net.0.proj.weight, transformer_blocks.1.ff_context.net.2.weight,
                         single_transformer_blocks.15.attn.to_q.weight, single_transformer_blocks.36.proj_mlp.weight,
                         single_transformer_blocks.33.proj_out.weight, transformer_blocks.4.attn.to_k.weight,
                         transformer_blocks.15.attn.add_q_proj.weight, transformer_blocks.4.attn.to_add_out.weight,
                         transformer_blocks.1.attn.to_add_out.weight, single_transformer_blocks.28.attn.to_v.weight,
                         transformer_blocks.11.attn.to_k.weight, transformer_blocks.5.attn.to_q.weight,
                         transformer_blocks.17.attn.add_q_proj.weight, transformer_blocks.10.attn.add_q_proj.weight,
                         transformer_blocks.7.attn.to_k.weight, single_transformer_blocks.17.proj_mlp.weight,
                         single_transformer_blocks.26.attn.to_k.weight, single_transformer_blocks.29.attn.to_k.weight,
                         single_transformer_blocks.34.attn.to_q.weight, single_transformer_blocks.25.proj_mlp.weight,
                         transformer_blocks.1.attn.to_k.weight, single_transformer_blocks.19.attn.to_q.weight,
                         transformer_blocks.0.attn.to_v.weight, transformer_blocks.2.attn.to_v.weight,
                         transformer_blocks.8.ff_context.net.2.weight, transformer_blocks.9.norm1_context.linear.weight,
                         single_transformer_blocks.1.attn.to_q.weight, single_transformer_blocks.19.proj_mlp.weight,
                         transformer_blocks.8.attn.to_out.0.weight, single_transformer_blocks.30.proj_mlp.weight,
                         single_transformer_blocks.28.attn.to_k.weight, single_transformer_blocks.12.proj_out.weight,
                         transformer_blocks.6.attn.to_v.weight, transformer_blocks.2.ff.net.2.weight,
                         single_transformer_blocks.23.proj_mlp.weight, transformer_blocks.12.attn.to_v.weight,
                         single_transformer_blocks.34.norm.linear.weight, transformer_blocks.18.ff.net.2.weight,
                         single_transformer_blocks.29.attn.to_q.weight, single_transformer_blocks.9.proj_mlp.weight,
                         single_transformer_blocks.12.attn.to_q.weight, single_transformer_blocks.7.attn.to_v.weight,
                         single_transformer_blocks.9.proj_out.weight, transformer_blocks.16.attn.to_add_out.weight,
                         transformer_blocks.3.ff.net.2.weight, single_transformer_blocks.6.attn.to_v.weight,
                         transformer_blocks.9.ff_context.net.2.weight, single_transformer_blocks.20.proj_mlp.weight,
                         transformer_blocks.8.norm1_context.linear.weight,
                         single_transformer_blocks.20.attn.to_v.weight, single_transformer_blocks.21.proj_out.weight,
                         transformer_blocks.5.ff.net.2.weight, transformer_blocks.7.attn.to_v.weight,
                         transformer_blocks.10.ff.net.0.proj.weight, transformer_blocks.9.attn.add_q_proj.weight,
                         single_transformer_blocks.13.proj_out.weight, single_transformer_blocks.2.proj_mlp.weight,
                         time_text_embed.guidance_embedder.linear_1.weight, transformer_blocks.11.attn.to_q.weight,
                         transformer_blocks.8.ff_context.net.0.proj.weight, transformer_blocks.9.norm1.linear.weight,
                         single_transformer_blocks.22.attn.to_k.weight,
                         transformer_blocks.6.norm1_context.linear.weight,
                         single_transformer_blocks.15.attn.to_v.weight, single_transformer_blocks.21.attn.to_v.weight,
                         single_transformer_blocks.34.proj_mlp.weight, transformer_blocks.13.attn.to_q.weight,
                         transformer_blocks.4.norm1.linear.weight, transformer_blocks.10.attn.to_v.weight,
                         single_transformer_blocks.4.norm.linear.weight,
                         transformer_blocks.1.ff_context.net.0.proj.weight,
                         single_transformer_blocks.14.proj_out.weight, transformer_blocks.16.attn.to_k.weight,
                         single_transformer_blocks.37.proj_out.weight, transformer_blocks.18.ff_context.net.2.weight,
                         transformer_blocks.0.attn.to_k.weight, transformer_blocks.16.ff.net.2.weight,
                         transformer_blocks.18.ff_context.net.0.proj.weight,
                         transformer_blocks.8.attn.add_k_proj.weight, single_transformer_blocks.18.attn.to_v.weight,
                         single_transformer_blocks.28.proj_out.weight, single_transformer_blocks.5.attn.to_q.weight,
                         single_transformer_blocks.32.attn.to_k.weight, transformer_blocks.6.attn.to_add_out.weight,
                         transformer_blocks.2.norm1_context.linear.weight,
                         single_transformer_blocks.32.norm.linear.weight,
                         single_transformer_blocks.37.norm.linear.weight,
                         single_transformer_blocks.6.norm.linear.weight, single_transformer_blocks.10.proj_mlp.weight,
                         single_transformer_blocks.6.proj_out.weight, single_transformer_blocks.30.attn.to_v.weight,
                         single_transformer_blocks.27.norm.linear.weight, transformer_blocks.2.norm1.linear.weight,
                         transformer_blocks.12.attn.add_v_proj.weight, single_transformer_blocks.36.attn.to_v.weight,
                         single_transformer_blocks.25.norm.linear.weight, single_transformer_blocks.25.attn.to_v.weight,
                         single_transformer_blocks.12.proj_mlp.weight, transformer_blocks.3.attn.add_q_proj.weight,
                         single_transformer_blocks.18.proj_out.weight, transformer_blocks.18.attn.add_q_proj.weight,
                         transformer_blocks.6.attn.add_k_proj.weight, transformer_blocks.18.attn.to_v.weight,
                         single_transformer_blocks.25.attn.to_k.weight, transformer_blocks.1.attn.to_v.weight,
                         single_transformer_blocks.2.attn.to_v.weight, single_transformer_blocks.11.norm.linear.weight,
                         single_transformer_blocks.18.attn.to_k.weight, transformer_blocks.12.attn.to_add_out.weight,
                         transformer_blocks.0.attn.to_out.0.weight, transformer_blocks.6.ff.net.2.weight,
                         single_transformer_blocks.33.proj_mlp.weight, single_transformer_blocks.30.norm.linear.weight,
                         single_transformer_blocks.27.proj_mlp.weight, single_transformer_blocks.35.proj_out.weight,
                         transformer_blocks.10.ff.net.2.weight, single_transformer_blocks.26.proj_out.weight,
                         transformer_blocks.13.attn.to_add_out.weight, single_transformer_blocks.17.proj_out.weight,
                         single_transformer_blocks.19.proj_out.weight, transformer_blocks.4.ff.net.2.weight,
                         single_transformer_blocks.0.norm.linear.weight, single_transformer_blocks.37.attn.to_k.weight,
                         transformer_blocks.13.norm1.linear.weight, single_transformer_blocks.4.attn.to_k.weight,
                         single_transformer_blocks.2.attn.to_k.weight, transformer_blocks.9.attn.add_k_proj.weight,
                         transformer_blocks.2.attn.to_add_out.weight, single_transformer_blocks.37.attn.to_v.weight,
                         single_transformer_blocks.9.norm.linear.weight, single_transformer_blocks.11.attn.to_q.weight,
                         transformer_blocks.11.attn.to_add_out.weight, transformer_blocks.10.norm1.linear.weight,
                         proj_out.weight, transformer_blocks.9.attn.to_v.weight,
                         transformer_blocks.4.ff_context.net.0.proj.weight,
                         single_transformer_blocks.29.norm.linear.weight, transformer_blocks.11.attn.add_k_proj.weight,
                         single_transformer_blocks.35.attn.to_k.weight,
                         transformer_blocks.11.norm1_context.linear.weight, transformer_blocks.15.ff.net.0.proj.weight,
                         transformer_blocks.13.attn.to_k.weight, transformer_blocks.13.norm1_context.linear.weight,
                         single_transformer_blocks.22.proj_out.weight,
                         transformer_blocks.14.norm1_context.linear.weight,
                         single_transformer_blocks.14.attn.to_v.weight, single_transformer_blocks.4.proj_mlp.weight,
                         single_transformer_blocks.1.proj_out.weight, transformer_blocks.3.attn.to_v.weight,
                         single_transformer_blocks.11.proj_out.weight, single_transformer_blocks.21.proj_mlp.weight,
                         transformer_blocks.2.attn.add_v_proj.weight, transformer_blocks.6.attn.add_v_proj.weight,
                         single_transformer_blocks.15.attn.to_k.weight, single_transformer_blocks.29.proj_mlp.weight,
                         single_transformer_blocks.19.norm.linear.weight, transformer_blocks.14.attn.to_k.weight,
                         transformer_blocks.3.attn.to_q.weight, single_transformer_blocks.34.proj_out.weight,
                         single_transformer_blocks.3.proj_out.weight, transformer_blocks.16.norm1.linear.weight,
                         transformer_blocks.14.attn.add_v_proj.weight, transformer_blocks.16.attn.add_v_proj.weight,
                         transformer_blocks.0.norm1.linear.weight, single_transformer_blocks.23.attn.to_k.weight,
                         single_transformer_blocks.10.attn.to_v.weight, transformer_blocks.1.attn.to_out.0.weight,
                         single_transformer_blocks.32.attn.to_q.weight, single_transformer_blocks.16.proj_out.weight,
                         single_transformer_blocks.17.attn.to_v.weight, transformer_blocks.4.attn.add_v_proj.weight,
                         transformer_blocks.10.attn.to_out.0.weight, single_transformer_blocks.8.norm.linear.weight,
                         transformer_blocks.10.attn.to_k.weight, single_transformer_blocks.4.proj_out.weight,
                         single_transformer_blocks.18.attn.to_q.weight,
                         transformer_blocks.16.norm1_context.linear.weight,
                         single_transformer_blocks.7.attn.to_k.weight, transformer_blocks.8.attn.add_v_proj.weight,
                         single_transformer_blocks.31.norm.linear.weight, transformer_blocks.0.attn.add_q_proj.weight,
                         single_transformer_blocks.34.attn.to_v.weight, single_transformer_blocks.36.norm.linear.weight,
                         single_transformer_blocks.7.norm.linear.weight, transformer_blocks.7.attn.to_q.weight,
                         transformer_blocks.2.ff.net.0.proj.weight, transformer_blocks.5.norm1.linear.weight,
                         transformer_blocks.8.attn.to_v.weight, transformer_blocks.4.norm1_context.linear.weight,
                         single_transformer_blocks.15.norm.linear.weight, single_transformer_blocks.30.proj_out.weight,
                         single_transformer_blocks.19.attn.to_k.weight,
                         transformer_blocks.10.norm1_context.linear.weight, transformer_blocks.9.attn.to_q.weight,
                         transformer_blocks.14.attn.to_v.weight, transformer_blocks.6.attn.add_q_proj.weight,
                         single_transformer_blocks.11.proj_mlp.weight, transformer_blocks.13.attn.add_v_proj.weight,
                         single_transformer_blocks.3.attn.to_q.weight, single_transformer_blocks.19.attn.to_v.weight,
                         single_transformer_blocks.7.proj_out.weight, transformer_blocks.6.ff.net.0.proj.weight,
                         transformer_blocks.11.ff.net.0.proj.weight, single_transformer_blocks.14.attn.to_q.weight,
                         single_transformer_blocks.31.attn.to_q.weight, single_transformer_blocks.4.attn.to_v.weight,
                         single_transformer_blocks.0.attn.to_v.weight,
                         transformer_blocks.14.ff_context.net.0.proj.weight,
                         single_transformer_blocks.35.attn.to_q.weight, single_transformer_blocks.13.attn.to_k.weight,
                         transformer_blocks.11.ff.net.2.weight, single_transformer_blocks.6.attn.to_k.weight,
                         transformer_blocks.7.attn.add_k_proj.weight, transformer_blocks.12.attn.add_q_proj.weight,
                         transformer_blocks.15.attn.to_q.weight, single_transformer_blocks.33.attn.to_v.weight,
                         single_transformer_blocks.12.attn.to_k.weight,
                         transformer_blocks.6.ff_context.net.0.proj.weight,
                         transformer_blocks.7.norm1_context.linear.weight,
                         single_transformer_blocks.37.attn.to_q.weight, single_transformer_blocks.9.attn.to_k.weight,
                         transformer_blocks.14.ff.net.0.proj.weight, single_transformer_blocks.11.attn.to_v.weight,
                         transformer_blocks.9.attn.to_out.0.weight, single_transformer_blocks.4.attn.to_q.weight,
                         transformer_blocks.15.attn.to_v.weight, transformer_blocks.17.ff_context.net.0.proj.weight,
                         transformer_blocks.1.norm1.linear.weight, transformer_blocks.6.attn.to_q.weight,
                         transformer_blocks.2.attn.add_k_proj.weight, transformer_blocks.7.ff_context.net.0.proj.weight,
                         single_transformer_blocks.16.attn.to_v.weight, transformer_blocks.10.attn.to_add_out.weight,
                         transformer_blocks.3.attn.add_v_proj.weight, transformer_blocks.13.attn.add_q_proj.weight,
                         transformer_blocks.2.attn.to_out.0.weight, single_transformer_blocks.20.attn.to_q.weight,
                         single_transformer_blocks.13.attn.to_q.weight, transformer_blocks.7.ff.net.0.proj.weight,
                         transformer_blocks.16.attn.add_q_proj.weight, single_transformer_blocks.8.attn.to_q.weight,
                         transformer_blocks.11.attn.add_v_proj.weight, single_transformer_blocks.18.norm.linear.weight,
                         context_embedder.weight, single_transformer_blocks.33.attn.to_k.weight,
                         time_text_embed.text_embedder.linear_2.weight, single_transformer_blocks.9.attn.to_v.weight,
                         single_transformer_blocks.3.attn.to_v.weight, single_transformer_blocks.23.proj_out.weight,
                         single_transformer_blocks.5.proj_out.weight, single_transformer_blocks.35.norm.linear.weight,
                         single_transformer_blocks.14.norm.linear.weight,
                         single_transformer_blocks.33.norm.linear.weight,
                         single_transformer_blocks.28.norm.linear.weight, transformer_blocks.11.attn.to_out.0.weight,
                         transformer_blocks.2.ff_context.net.2.weight,
                         transformer_blocks.2.ff_context.net.0.proj.weight,
                         single_transformer_blocks.28.proj_mlp.weight, single_transformer_blocks.27.attn.to_v.weight,
                         single_transformer_blocks.32.attn.to_v.weight.
                          Please make sure to pass `low_cpu_mem_usage=False` and `device_map=None` if you want to
                         randomly initialize those weights or else make sure your checkpoint file is correct.
17:59:43-971024 ERROR    Load: ValueError
╭───────────────────────────────────────── Traceback (most recent call last) ──────────────────────────────────────────╮
│ C:\ai\automatic\modules\sd_models.py:1156 in load_diffuser                                                           │
│                                                                                                                      │
│   1155 │   │   │   │   │   from modules.model_flux import load_flux                                                  │
│ ❱ 1156 │   │   │   │   │   sd_model = load_flux(checkpoint_info, diffusers_load_config)                              │
│   1157 │   │   │   │   except Exception as e:                                                                        │
│                                                                                                                      │
│ C:\ai\automatic\modules\model_flux.py:241 in load_flux                                                               │
│                                                                                                                      │
│   240 │   shared.log.debug(f'Loading FLUX: preloaded={list(components)}')                                            │
│ ❱ 241 │   pipe = diffusers.FluxPipeline.from_pretrained(repo_id, cache_dir=shared.opts.diffusers_dir, **components,  │
│   242 │   return pipe                                                                                                │
│                                                                                                                      │
│ c:\ai\automatic\venv\Lib\site-packages\huggingface_hub\utils\_validators.py:114 in _inner_fn                         │
│                                                                                                                      │
│   113 │   │                                                                                                          │
│ ❱ 114 │   │   return fn(*args, **kwargs)                                                                             │
│   115                                                                                                                │
│                                                                                                                      │
│ c:\ai\automatic\venv\Lib\site-packages\diffusers\pipelines\pipeline_utils.py:859 in from_pretrained                  │
│                                                                                                                      │
│    858 │   │   │   │   # load sub model                                                                              │
│ ❱  859 │   │   │   │   loaded_sub_model = load_sub_model(                                                            │
│    860 │   │   │   │   │   library_name=library_name,                                                                │
│                                                                                                                      │
│ c:\ai\automatic\venv\Lib\site-packages\diffusers\pipelines\pipeline_loading_utils.py:698 in load_sub_model           │
│                                                                                                                      │
│   697 │   if os.path.isdir(os.path.join(cached_folder, name)):                                                       │
│ ❱ 698 │   │   loaded_sub_model = load_method(os.path.join(cached_folder, name), **loading_kwargs)                    │
│   699 │   else:                                                                                                      │
│                                                                                                                      │
│ c:\ai\automatic\venv\Lib\site-packages\huggingface_hub\utils\_validators.py:114 in _inner_fn                         │
│                                                                                                                      │
│   113 │   │                                                                                                          │
│ ❱ 114 │   │   return fn(*args, **kwargs)                                                                             │
│   115                                                                                                                │
│                                                                                                                      │
│ c:\ai\automatic\venv\Lib\site-packages\diffusers\models\modeling_utils.py:740 in from_pretrained                     │
│                                                                                                                      │
│    739 │   │   │   │   │   if len(missing_keys) > 0:                                                                 │
│ ❱  740 │   │   │   │   │   │   raise ValueError(                                                                     │
│    741 │   │   │   │   │   │   │   f"Cannot load {cls} from {pretrained_model_name_or_path} because the following ke │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
ValueError: Cannot load <class 'diffusers.models.transformers.transformer_flux.FluxTransformer2DModel'> from models\Diffusers\models--Disty0--FLUX.1-dev-qint4\snapshots\82811df42b556a1153b971d8375d5170c306a6eb\transformer because the following keys are missing:
 transformer_blocks.2.attn.to_k.weight, transformer_blocks.8.norm1.linear.weight, transformer_blocks.5.attn.add_v_proj.weight, transformer_blocks.16.ff_context.net.2.weight, transformer_blocks.0.attn.to_add_out.weight, transformer_blocks.8.attn.to_k.weight, transformer_blocks.5.norm1_context.linear.weight, transformer_blocks.13.attn.add_k_proj.weight, transformer_blocks.0.ff.net.2.weight, single_transformer_blocks.23.norm.linear.weight, single_transformer_blocks.24.norm.linear.weight, transformer_blocks.8.attn.to_q.weight, single_transformer_blocks.28.attn.to_q.weight, single_transformer_blocks.20.norm.linear.weight, single_transformer_blocks.36.proj_out.weight, transformer_blocks.11.attn.add_q_proj.weight, transformer_blocks.12.attn.to_k.weight, single_transformer_blocks.6.proj_mlp.weight, single_transformer_blocks.27.proj_out.weight, transformer_blocks.1.attn.add_k_proj.weight, single_transformer_blocks.2.norm.linear.weight, transformer_blocks.4.attn.add_q_proj.weight, transformer_blocks.12.attn.to_out.0.weight, single_transformer_blocks.32.proj_out.weight, single_transformer_blocks.3.norm.linear.weight, transformer_blocks.5.ff_context.net.2.weight, transformer_blocks.9.attn.to_k.weight, transformer_blocks.12.ff.net.2.weight, single_transformer_blocks.0.attn.to_q.weight, time_text_embed.timestep_embedder.linear_1.weight, transformer_blocks.12.ff_context.net.2.weight, transformer_blocks.5.ff.net.0.proj.weight, single_transformer_blocks.21.attn.to_k.weight, transformer_blocks.0.ff_context.net.2.weight, single_transformer_blocks.23.attn.to_v.weight, transformer_blocks.5.attn.to_k.weight, transformer_blocks.9.ff.net.0.proj.weight, single_transformer_blocks.35.attn.to_v.weight, single_transformer_blocks.25.attn.to_q.weight, transformer_blocks.8.attn.add_q_proj.weight, single_transformer_blocks.0.attn.to_k.weight, transformer_blocks.18.attn.to_q.weight, single_transformer_blocks.2.proj_out.weight, single_transformer_blocks.24.proj_out.weight, transformer_blocks.5.attn.to_out.0.weight, single_transformer_blocks.8.attn.to_k.weight, transformer_blocks.18.attn.add_k_proj.weight, single_transformer_blocks.22.proj_mlp.weight, transformer_blocks.16.ff_context.net.0.proj.weight, transformer_blocks.17.attn.to_k.weight, single_transformer_blocks.18.proj_mlp.weight, transformer_blocks.15.ff.net.2.weight, transformer_blocks.7.ff_context.net.2.weight, single_transformer_blocks.36.attn.to_q.weight, transformer_blocks.13.attn.to_v.weight, single_transformer_blocks.34.attn.to_k.weight, single_transformer_blocks.12.attn.to_v.weight, single_transformer_blocks.22.norm.linear.weight, transformer_blocks.10.ff_context.net.2.weight, transformer_blocks.0.attn.add_k_proj.weight, transformer_blocks.9.attn.to_add_out.weight, single_transformer_blocks.26.proj_mlp.weight, transformer_blocks.6.attn.to_out.0.weight, single_transformer_blocks.13.norm.linear.weight, single_transformer_blocks.11.attn.to_k.weight, transformer_blocks.1.attn.add_v_proj.weight, transformer_blocks.1.attn.to_q.weight, transformer_blocks.15.ff_context.net.2.weight, transformer_blocks.15.attn.to_add_out.weight, single_transformer_blocks.0.proj_out.weight, transformer_blocks.4.attn.add_k_proj.weight, transformer_blocks.3.norm1_context.linear.weight, single_transformer_blocks.3.proj_mlp.weight, single_transformer_blocks.17.attn.to_k.weight, transformer_blocks.5.attn.to_v.weight, single_transformer_blocks.5.norm.linear.weight, single_transformer_blocks.10.norm.linear.weight, single_transformer_blocks.0.proj_mlp.weight, transformer_blocks.9.ff_context.net.0.proj.weight, transformer_blocks.13.ff.net.0.proj.weight, single_transformer_blocks.8.proj_out.weight, transformer_blocks.0.attn.to_q.weight, transformer_blocks.14.ff.net.2.weight, transformer_blocks.1.attn.add_q_proj.weight, transformer_blocks.16.ff.net.0.proj.weight, transformer_blocks.18.norm1.linear.weight, transformer_blocks.1.ff.net.0.proj.weight, transformer_blocks.3.attn.add_k_proj.weight, transformer_blocks.14.attn.to_q.weight, transformer_blocks.9.attn.add_v_proj.weight, single_transformer_blocks.36.attn.to_k.weight, single_transformer_blocks.3.attn.to_k.weight, transformer_blocks.7.attn.add_v_proj.weight, single_transformer_blocks.7.attn.to_q.weight, transformer_blocks.17.ff.net.0.proj.weight, transformer_blocks.4.attn.to_out.0.weight, transformer_blocks.4.attn.to_q.weight, single_transformer_blocks.30.attn.to_q.weight, transformer_blocks.5.ff_context.net.0.proj.weight, transformer_blocks.12.norm1.linear.weight, transformer_blocks.14.attn.to_add_out.weight, single_transformer_blocks.2.attn.to_q.weight, transformer_blocks.6.attn.to_k.weight, transformer_blocks.11.ff_context.net.2.weight, transformer_blocks.16.attn.to_q.weight, transformer_blocks.8.ff.net.2.weight, single_transformer_blocks.23.attn.to_q.weight, norm_out.linear.weight, single_transformer_blocks.7.proj_mlp.weight, transformer_blocks.10.attn.add_v_proj.weight, transformer_blocks.16.attn.to_out.0.weight, single_transformer_blocks.1.attn.to_v.weight, single_transformer_blocks.33.attn.to_q.weight, transformer_blocks.11.attn.to_v.weight, single_transformer_blocks.26.attn.to_q.weight, single_transformer_blocks.9.attn.to_q.weight, transformer_blocks.12.ff_context.net.0.proj.weight, transformer_blocks.5.attn.add_k_proj.weight, transformer_blocks.18.attn.to_out.0.weight, transformer_blocks.6.ff_context.net.2.weight, transformer_blocks.12.attn.add_k_proj.weight, transformer_blocks.15.attn.add_v_proj.weight, single_transformer_blocks.26.attn.to_v.weight, time_text_embed.text_embedder.linear_1.weight, transformer_blocks.18.norm1_context.linear.weight, transformer_blocks.14.attn.to_out.0.weight, single_transformer_blocks.6.attn.to_q.weight, transformer_blocks.17.attn.to_add_out.weight, transformer_blocks.10.attn.to_q.weight, transformer_blocks.17.norm1_context.linear.weight, transformer_blocks.3.ff_context.net.0.proj.weight, single_transformer_blocks.15.proj_out.weight, transformer_blocks.8.attn.to_add_out.weight, transformer_blocks.10.ff_context.net.0.proj.weight, single_transformer_blocks.24.attn.to_k.weight, transformer_blocks.13.ff_context.net.2.weight, transformer_blocks.16.attn.to_v.weight, transformer_blocks.10.attn.add_k_proj.weight, transformer_blocks.7.attn.add_q_proj.weight, single_transformer_blocks.26.norm.linear.weight, transformer_blocks.11.ff_context.net.0.proj.weight, single_transformer_blocks.13.attn.to_v.weight, single_transformer_blocks.16.proj_mlp.weight, single_transformer_blocks.13.proj_mlp.weight, transformer_blocks.14.norm1.linear.weight, single_transformer_blocks.1.norm.linear.weight, single_transformer_blocks.1.proj_mlp.weight, single_transformer_blocks.16.norm.linear.weight, transformer_blocks.17.attn.to_out.0.weight, transformer_blocks.5.attn.to_add_out.weight, transformer_blocks.13.ff.net.2.weight, transformer_blocks.12.ff.net.0.proj.weight, transformer_blocks.3.attn.to_out.0.weight, transformer_blocks.15.attn.to_out.0.weight, transformer_blocks.14.ff_context.net.2.weight, transformer_blocks.15.attn.add_k_proj.weight, transformer_blocks.17.ff_context.net.2.weight, single_transformer_blocks.8.attn.to_v.weight, time_text_embed.timestep_embedder.linear_2.weight, single_transformer_blocks.10.attn.to_q.weight, single_transformer_blocks.12.norm.linear.weight, transformer_blocks.4.attn.to_v.weight, single_transformer_blocks.24.attn.to_q.weight, transformer_blocks.0.norm1_context.linear.weight, transformer_blocks.17.norm1.linear.weight, transformer_blocks.18.attn.to_add_out.weight, single_transformer_blocks.24.attn.to_v.weight, single_transformer_blocks.25.proj_out.weight, transformer_blocks.12.norm1_context.linear.weight, single_transformer_blocks.10.attn.to_k.weight, single_transformer_blocks.15.proj_mlp.weight, single_transformer_blocks.31.attn.to_k.weight, transformer_blocks.5.attn.add_q_proj.weight, transformer_blocks.18.attn.to_k.weight, transformer_blocks.3.ff.net.0.proj.weight, single_transformer_blocks.20.proj_out.weight, time_text_embed.guidance_embedder.linear_2.weight, transformer_blocks.18.attn.add_v_proj.weight, single_transformer_blocks.21.norm.linear.weight, transformer_blocks.17.attn.add_k_proj.weight, transformer_blocks.17.attn.to_v.weight, transformer_blocks.9.ff.net.2.weight, transformer_blocks.17.ff.net.2.weight, single_transformer_blocks.14.proj_mlp.weight, x_embedder.weight, single_transformer_blocks.30.attn.to_k.weight, transformer_blocks.0.attn.add_v_proj.weight, single_transformer_blocks.31.proj_mlp.weight, single_transformer_blocks.32.proj_mlp.weight, transformer_blocks.14.attn.add_k_proj.weight, single_transformer_blocks.16.attn.to_q.weight, single_transformer_blocks.27.attn.to_q.weight, transformer_blocks.15.attn.to_k.weight, single_transformer_blocks.10.proj_out.weight, transformer_blocks.1.ff.net.2.weight, transformer_blocks.7.attn.to_add_out.weight, single_transformer_blocks.8.proj_mlp.weight, single_transformer_blocks.5.attn.to_v.weight, transformer_blocks.14.attn.add_q_proj.weight, transformer_blocks.11.norm1.linear.weight, single_transformer_blocks.31.proj_out.weight, transformer_blocks.2.attn.to_q.weight, transformer_blocks.16.attn.add_k_proj.weight, transformer_blocks.8.ff.net.0.proj.weight, single_transformer_blocks.22.attn.to_v.weight, single_transformer_blocks.17.attn.to_q.weight, transformer_blocks.18.ff.net.0.proj.weight, transformer_blocks.3.attn.to_add_out.weight, single_transformer_blocks.16.attn.to_k.weight, transformer_blocks.17.attn.add_v_proj.weight, single_transformer_blocks.1.attn.to_k.weight, single_transformer_blocks.29.proj_out.weight, transformer_blocks.3.attn.to_k.weight, single_transformer_blocks.21.attn.to_q.weight, transformer_blocks.15.norm1_context.linear.weight, transformer_blocks.13.ff_context.net.0.proj.weight, transformer_blocks.1.norm1_context.linear.weight, transformer_blocks.2.attn.add_q_proj.weight, transformer_blocks.6.norm1.linear.weight, single_transformer_blocks.31.attn.to_v.weight, single_transformer_blocks.17.norm.linear.weight, transformer_blocks.15.norm1.linear.weight, transformer_blocks.15.ff_context.net.0.proj.weight, single_transformer_blocks.37.proj_mlp.weight, transformer_blocks.0.ff_context.net.0.proj.weight, transformer_blocks.12.attn.to_q.weight, single_transformer_blocks.24.proj_mlp.weight, single_transformer_blocks.5.proj_mlp.weight, single_transformer_blocks.35.proj_mlp.weight, single_transformer_blocks.20.attn.to_k.weight, transformer_blocks.13.attn.to_out.0.weight, transformer_blocks.7.norm1.linear.weight, transformer_blocks.3.ff_context.net.2.weight, single_transformer_blocks.22.attn.to_q.weight, transformer_blocks.4.ff_context.net.2.weight, transformer_blocks.17.attn.to_q.weight, transformer_blocks.7.attn.to_out.0.weight, single_transformer_blocks.27.attn.to_k.weight, single_transformer_blocks.5.attn.to_k.weight, transformer_blocks.7.ff.net.2.weight, single_transformer_blocks.14.attn.to_k.weight, transformer_blocks.4.ff.net.0.proj.weight, single_transformer_blocks.29.attn.to_v.weight, transformer_blocks.3.norm1.linear.weight, transformer_blocks.0.ff.net.0.proj.weight, transformer_blocks.1.ff_context.net.2.weight, single_transformer_blocks.15.attn.to_q.weight, single_transformer_blocks.36.proj_mlp.weight, single_transformer_blocks.33.proj_out.weight, transformer_blocks.4.attn.to_k.weight, transformer_blocks.15.attn.add_q_proj.weight, transformer_blocks.4.attn.to_add_out.weight, transformer_blocks.1.attn.to_add_out.weight, single_transformer_blocks.28.attn.to_v.weight, transformer_blocks.11.attn.to_k.weight, transformer_blocks.5.attn.to_q.weight, transformer_blocks.17.attn.add_q_proj.weight, transformer_blocks.10.attn.add_q_proj.weight, transformer_blocks.7.attn.to_k.weight, single_transformer_blocks.17.proj_mlp.weight, single_transformer_blocks.26.attn.to_k.weight, single_transformer_blocks.29.attn.to_k.weight, single_transformer_blocks.34.attn.to_q.weight, single_transformer_blocks.25.proj_mlp.weight, transformer_blocks.1.attn.to_k.weight, single_transformer_blocks.19.attn.to_q.weight, transformer_blocks.0.attn.to_v.weight, transformer_blocks.2.attn.to_v.weight, transformer_blocks.8.ff_context.net.2.weight, transformer_blocks.9.norm1_context.linear.weight, single_transformer_blocks.1.attn.to_q.weight, single_transformer_blocks.19.proj_mlp.weight, transformer_blocks.8.attn.to_out.0.weight, single_transformer_blocks.30.proj_mlp.weight, single_transformer_blocks.28.attn.to_k.weight, single_transformer_blocks.12.proj_out.weight, transformer_blocks.6.attn.to_v.weight, transformer_blocks.2.ff.net.2.weight, single_transformer_blocks.23.proj_mlp.weight, transformer_blocks.12.attn.to_v.weight, single_transformer_blocks.34.norm.linear.weight, transformer_blocks.18.ff.net.2.weight, single_transformer_blocks.29.attn.to_q.weight, single_transformer_blocks.9.proj_mlp.weight, single_transformer_blocks.12.attn.to_q.weight, single_transformer_blocks.7.attn.to_v.weight, single_transformer_blocks.9.proj_out.weight, transformer_blocks.16.attn.to_add_out.weight, transformer_blocks.3.ff.net.2.weight, single_transformer_blocks.6.attn.to_v.weight, transformer_blocks.9.ff_context.net.2.weight, single_transformer_blocks.20.proj_mlp.weight, transformer_blocks.8.norm1_context.linear.weight, single_transformer_blocks.20.attn.to_v.weight, single_transformer_blocks.21.proj_out.weight, transformer_blocks.5.ff.net.2.weight, transformer_blocks.7.attn.to_v.weight, transformer_blocks.10.ff.net.0.proj.weight, transformer_blocks.9.attn.add_q_proj.weight, single_transformer_blocks.13.proj_out.weight, single_transformer_blocks.2.proj_mlp.weight, time_text_embed.guidance_embedder.linear_1.weight, transformer_blocks.11.attn.to_q.weight, transformer_blocks.8.ff_context.net.0.proj.weight, transformer_blocks.9.norm1.linear.weight, single_transformer_blocks.22.attn.to_k.weight, transformer_blocks.6.norm1_context.linear.weight, single_transformer_blocks.15.attn.to_v.weight, single_transformer_blocks.21.attn.to_v.weight, single_transformer_blocks.34.proj_mlp.weight, transformer_blocks.13.attn.to_q.weight, transformer_blocks.4.norm1.linear.weight, transformer_blocks.10.attn.to_v.weight, single_transformer_blocks.4.norm.linear.weight, transformer_blocks.1.ff_context.net.0.proj.weight, single_transformer_blocks.14.proj_out.weight, transformer_blocks.16.attn.to_k.weight, single_transformer_blocks.37.proj_out.weight, transformer_blocks.18.ff_context.net.2.weight, transformer_blocks.0.attn.to_k.weight, transformer_blocks.16.ff.net.2.weight, transformer_blocks.18.ff_context.net.0.proj.weight, transformer_blocks.8.attn.add_k_proj.weight, single_transformer_blocks.18.attn.to_v.weight, single_transformer_blocks.28.proj_out.weight, single_transformer_blocks.5.attn.to_q.weight, single_transformer_blocks.32.attn.to_k.weight, transformer_blocks.6.attn.to_add_out.weight, transformer_blocks.2.norm1_context.linear.weight, single_transformer_blocks.32.norm.linear.weight, single_transformer_blocks.37.norm.linear.weight, single_transformer_blocks.6.norm.linear.weight, single_transformer_blocks.10.proj_mlp.weight, single_transformer_blocks.6.proj_out.weight, single_transformer_blocks.30.attn.to_v.weight, single_transformer_blocks.27.norm.linear.weight, transformer_blocks.2.norm1.linear.weight, transformer_blocks.12.attn.add_v_proj.weight, single_transformer_blocks.36.attn.to_v.weight, single_transformer_blocks.25.norm.linear.weight, single_transformer_blocks.25.attn.to_v.weight, single_transformer_blocks.12.proj_mlp.weight, transformer_blocks.3.attn.add_q_proj.weight, single_transformer_blocks.18.proj_out.weight, transformer_blocks.18.attn.add_q_proj.weight, transformer_blocks.6.attn.add_k_proj.weight, transformer_blocks.18.attn.to_v.weight, single_transformer_blocks.25.attn.to_k.weight, transformer_blocks.1.attn.to_v.weight, single_transformer_blocks.2.attn.to_v.weight, single_transformer_blocks.11.norm.linear.weight, single_transformer_blocks.18.attn.to_k.weight, transformer_blocks.12.attn.to_add_out.weight, transformer_blocks.0.attn.to_out.0.weight, transformer_blocks.6.ff.net.2.weight, single_transformer_blocks.33.proj_mlp.weight, single_transformer_blocks.30.norm.linear.weight, single_transformer_blocks.27.proj_mlp.weight, single_transformer_blocks.35.proj_out.weight, transformer_blocks.10.ff.net.2.weight, single_transformer_blocks.26.proj_out.weight, transformer_blocks.13.attn.to_add_out.weight, single_transformer_blocks.17.proj_out.weight, single_transformer_blocks.19.proj_out.weight, transformer_blocks.4.ff.net.2.weight, single_transformer_blocks.0.norm.linear.weight, single_transformer_blocks.37.attn.to_k.weight, transformer_blocks.13.norm1.linear.weight, single_transformer_blocks.4.attn.to_k.weight, single_transformer_blocks.2.attn.to_k.weight, transformer_blocks.9.attn.add_k_proj.weight, transformer_blocks.2.attn.to_add_out.weight, single_transformer_blocks.37.attn.to_v.weight, single_transformer_blocks.9.norm.linear.weight, single_transformer_blocks.11.attn.to_q.weight, transformer_blocks.11.attn.to_add_out.weight, transformer_blocks.10.norm1.linear.weight, proj_out.weight, transformer_blocks.9.attn.to_v.weight, transformer_blocks.4.ff_context.net.0.proj.weight, single_transformer_blocks.29.norm.linear.weight, transformer_blocks.11.attn.add_k_proj.weight, single_transformer_blocks.35.attn.to_k.weight, transformer_blocks.11.norm1_context.linear.weight, transformer_blocks.15.ff.net.0.proj.weight, transformer_blocks.13.attn.to_k.weight, transformer_blocks.13.norm1_context.linear.weight, single_transformer_blocks.22.proj_out.weight, transformer_blocks.14.norm1_context.linear.weight, single_transformer_blocks.14.attn.to_v.weight, single_transformer_blocks.4.proj_mlp.weight, single_transformer_blocks.1.proj_out.weight, transformer_blocks.3.attn.to_v.weight, single_transformer_blocks.11.proj_out.weight, single_transformer_blocks.21.proj_mlp.weight, transformer_blocks.2.attn.add_v_proj.weight, transformer_blocks.6.attn.add_v_proj.weight, single_transformer_blocks.15.attn.to_k.weight, single_transformer_blocks.29.proj_mlp.weight, single_transformer_blocks.19.norm.linear.weight, transformer_blocks.14.attn.to_k.weight, transformer_blocks.3.attn.to_q.weight, single_transformer_blocks.34.proj_out.weight, single_transformer_blocks.3.proj_out.weight, transformer_blocks.16.norm1.linear.weight, transformer_blocks.14.attn.add_v_proj.weight, transformer_blocks.16.attn.add_v_proj.weight, transformer_blocks.0.norm1.linear.weight, single_transformer_blocks.23.attn.to_k.weight, single_transformer_blocks.10.attn.to_v.weight, transformer_blocks.1.attn.to_out.0.weight, single_transformer_blocks.32.attn.to_q.weight, single_transformer_blocks.16.proj_out.weight, single_transformer_blocks.17.attn.to_v.weight, transformer_blocks.4.attn.add_v_proj.weight, transformer_blocks.10.attn.to_out.0.weight, single_transformer_blocks.8.norm.linear.weight, transformer_blocks.10.attn.to_k.weight, single_transformer_blocks.4.proj_out.weight, single_transformer_blocks.18.attn.to_q.weight, transformer_blocks.16.norm1_context.linear.weight, single_transformer_blocks.7.attn.to_k.weight, transformer_blocks.8.attn.add_v_proj.weight, single_transformer_blocks.31.norm.linear.weight, transformer_blocks.0.attn.add_q_proj.weight, single_transformer_blocks.34.attn.to_v.weight, single_transformer_blocks.36.norm.linear.weight, single_transformer_blocks.7.norm.linear.weight, transformer_blocks.7.attn.to_q.weight, transformer_blocks.2.ff.net.0.proj.weight, transformer_blocks.5.norm1.linear.weight, transformer_blocks.8.attn.to_v.weight, transformer_blocks.4.norm1_context.linear.weight, single_transformer_blocks.15.norm.linear.weight, single_transformer_blocks.30.proj_out.weight, single_transformer_blocks.19.attn.to_k.weight, transformer_blocks.10.norm1_context.linear.weight, transformer_blocks.9.attn.to_q.weight, transformer_blocks.14.attn.to_v.weight, transformer_blocks.6.attn.add_q_proj.weight, single_transformer_blocks.11.proj_mlp.weight, transformer_blocks.13.attn.add_v_proj.weight, single_transformer_blocks.3.attn.to_q.weight, single_transformer_blocks.19.attn.to_v.weight, single_transformer_blocks.7.proj_out.weight, transformer_blocks.6.ff.net.0.proj.weight, transformer_blocks.11.ff.net.0.proj.weight, single_transformer_blocks.14.attn.to_q.weight, single_transformer_blocks.31.attn.to_q.weight, single_transformer_blocks.4.attn.to_v.weight, single_transformer_blocks.0.attn.to_v.weight, transformer_blocks.14.ff_context.net.0.proj.weight, single_transformer_blocks.35.attn.to_q.weight, single_transformer_blocks.13.attn.to_k.weight, transformer_blocks.11.ff.net.2.weight, single_transformer_blocks.6.attn.to_k.weight, transformer_blocks.7.attn.add_k_proj.weight, transformer_blocks.12.attn.add_q_proj.weight, transformer_blocks.15.attn.to_q.weight, single_transformer_blocks.33.attn.to_v.weight, single_transformer_blocks.12.attn.to_k.weight, transformer_blocks.6.ff_context.net.0.proj.weight, transformer_blocks.7.norm1_context.linear.weight, single_transformer_blocks.37.attn.to_q.weight, single_transformer_blocks.9.attn.to_k.weight, transformer_blocks.14.ff.net.0.proj.weight, single_transformer_blocks.11.attn.to_v.weight, transformer_blocks.9.attn.to_out.0.weight, single_transformer_blocks.4.attn.to_q.weight, transformer_blocks.15.attn.to_v.weight, transformer_blocks.17.ff_context.net.0.proj.weight, transformer_blocks.1.norm1.linear.weight, transformer_blocks.6.attn.to_q.weight, transformer_blocks.2.attn.add_k_proj.weight, transformer_blocks.7.ff_context.net.0.proj.weight, single_transformer_blocks.16.attn.to_v.weight, transformer_blocks.10.attn.to_add_out.weight, transformer_blocks.3.attn.add_v_proj.weight, transformer_blocks.13.attn.add_q_proj.weight, transformer_blocks.2.attn.to_out.0.weight, single_transformer_blocks.20.attn.to_q.weight, single_transformer_blocks.13.attn.to_q.weight, transformer_blocks.7.ff.net.0.proj.weight, transformer_blocks.16.attn.add_q_proj.weight, single_transformer_blocks.8.attn.to_q.weight, transformer_blocks.11.attn.add_v_proj.weight, single_transformer_blocks.18.norm.linear.weight, context_embedder.weight, single_transformer_blocks.33.attn.to_k.weight, time_text_embed.text_embedder.linear_2.weight, single_transformer_blocks.9.attn.to_v.weight, single_transformer_blocks.3.attn.to_v.weight, single_transformer_blocks.23.proj_out.weight, single_transformer_blocks.5.proj_out.weight, single_transformer_blocks.35.norm.linear.weight, single_transformer_blocks.14.norm.linear.weight, single_transformer_blocks.33.norm.linear.weight, single_transformer_blocks.28.norm.linear.weight, transformer_blocks.11.attn.to_out.0.weight, transformer_blocks.2.ff_context.net.2.weight, transformer_blocks.2.ff_context.net.0.proj.weight, single_transformer_blocks.28.proj_mlp.weight, single_transformer_blocks.27.attn.to_v.weight, single_transformer_blocks.32.attn.to_v.weight.
 Please make sure to pass `low_cpu_mem_usage=False` and `device_map=None` if you want to randomly initialize those weights or else make sure your checkpoint file is correct.
17:59:44-270221 DEBUG    Script callback init time: image_browser.py:ui_tabs=0.40 system-info.py:app_started=0.06
                         task_scheduler.py:app_started=0.13
17:59:44-271218 INFO     Startup time: 12.97 torch=4.12 gradio=1.28 diffusers=0.41 libraries=1.66 extensions=0.62
                         face-restore=0.20 ui-en=0.21 ui-txt2img=0.06 ui-img2img=0.21 ui-control=0.11 ui-settings=0.23
                         ui-extensions=1.02 ui-defaults=0.26 launch=0.13 api=0.09 app-started=0.19 checkpoint=1.95
17:59:44-273212 DEBUG    Save: file="config.json" json=35 bytes=1470 time=0.003
17:59:44-275207 DEBUG    Unused settings: ['cross_attention_options']
18:00:00-280156 DEBUG    Server: alive=True jobs=1 requests=3 uptime=23 memory=1.02/63.92 backend=Backend.DIFFUSERS
                         state=idle

ahhh, making (slow) progress. updated.

btw, no idea what this is about?

github-staff deleted a comment from SAC020

ahhh, making (slow) progress. updated.

btw, no idea what this is about?

github-staff deleted a comment from SAC020

Progress indeed, but still not working yet.

I have no idea what comment they've deleted, I haven't made any further comment

c:\ai\automatic>.\webui.bat --medvram --debug
Using VENV: c:\ai\automatic\venv
20:01:57-218835 INFO     Starting SD.Next
20:01:57-221827 INFO     Logger: file="c:\ai\automatic\sdnext.log" level=DEBUG size=65 mode=create
20:01:57-222825 INFO     Python version=3.11.9 platform=Windows bin="c:\ai\automatic\venv\Scripts\python.exe"
                         venv="c:\ai\automatic\venv"
20:01:57-433262 INFO     Version: app=sd.next updated=2024-09-04 hash=db6a52a7 branch=dev
                         url=https://github.com/vladmandic/automatic/tree/dev ui=dev
20:01:58-409638 INFO     Latest published version: bab17a0b4f91b41c885f10262ef8c8e70ba72faa 2024-08-31T20:57:34Z
20:01:58-423600 INFO     Platform: arch=AMD64 cpu=Intel64 Family 6 Model 165 Stepping 5, GenuineIntel system=Windows
                         release=Windows-10-10.0.22631-SP0 python=3.11.9
20:01:58-426592 DEBUG    Setting environment tuning
20:01:58-427590 INFO     HF cache folder: C:\Users\sebas\.cache\huggingface\hub
20:01:58-429585 DEBUG    Torch allocator: "garbage_collection_threshold:0.80,max_split_size_mb:512"
20:01:58-442550 DEBUG    Torch overrides: cuda=False rocm=False ipex=False diml=False openvino=False
20:01:58-443547 DEBUG    Torch allowed: cuda=True rocm=True ipex=True diml=True openvino=True
20:01:58-454549 INFO     nVidia CUDA toolkit detected: nvidia-smi present
20:01:58-562230 WARNING  Modified files: ['models/Reference/playgroundai--playground-v2-1024px-aesthetic.jpg']
20:01:58-664955 INFO     Verifying requirements
20:01:58-668944 INFO     Verifying packages
20:01:58-715819 DEBUG    Repository update time: Wed Sep  4 19:32:57 2024
20:01:58-716818 INFO     Startup: standard
20:01:58-717816 INFO     Verifying submodules
20:02:02-075255 DEBUG    Git detached head detected: folder="extensions-builtin/sd-extension-chainner" reattach=main
20:02:02-077279 DEBUG    Submodule: extensions-builtin/sd-extension-chainner / main
20:02:02-209895 DEBUG    Git detached head detected: folder="extensions-builtin/sd-extension-system-info" reattach=main
20:02:02-210893 DEBUG    Submodule: extensions-builtin/sd-extension-system-info / main
20:02:02-354509 DEBUG    Git detached head detected: folder="extensions-builtin/sd-webui-agent-scheduler" reattach=main
20:02:02-355506 DEBUG    Submodule: extensions-builtin/sd-webui-agent-scheduler / main
20:02:02-535277 DEBUG    Git detached head detected: folder="extensions-builtin/sdnext-modernui" reattach=dev
20:02:02-536274 DEBUG    Submodule: extensions-builtin/sdnext-modernui / dev
20:02:02-693852 DEBUG    Git detached head detected: folder="extensions-builtin/stable-diffusion-webui-rembg"
                         reattach=master
20:02:02-694849 DEBUG    Submodule: extensions-builtin/stable-diffusion-webui-rembg / master
20:02:02-823506 DEBUG    Git detached head detected: folder="modules/k-diffusion" reattach=master
20:02:02-824503 DEBUG    Submodule: modules/k-diffusion / master
20:02:02-956152 DEBUG    Git detached head detected: folder="wiki" reattach=master
20:02:02-957149 DEBUG    Submodule: wiki / master
20:02:03-122631 DEBUG    Register paths
20:02:03-218375 DEBUG    Installed packages: 209
20:02:03-220370 DEBUG    Extensions all: ['Lora', 'sd-extension-chainner', 'sd-extension-system-info',
                         'sd-webui-agent-scheduler', 'sd-webui-controlnet', 'sdnext-modernui',
                         'stable-diffusion-webui-images-browser', 'stable-diffusion-webui-rembg']
20:02:03-416844 DEBUG    Running extension installer:
                         C:\ai\automatic\extensions-builtin\sd-extension-system-info\install.py
20:02:03-859661 DEBUG    Running extension installer:
                         C:\ai\automatic\extensions-builtin\sd-webui-agent-scheduler\install.py
20:02:04-278540 DEBUG    Running extension installer: C:\ai\automatic\extensions-builtin\sd-webui-controlnet\install.py
20:02:04-874946 DEBUG    Running extension installer:
                         C:\ai\automatic\extensions-builtin\stable-diffusion-webui-images-browser\install.py
20:02:05-314770 DEBUG    Running extension installer:
                         C:\ai\automatic\extensions-builtin\stable-diffusion-webui-rembg\install.py
20:02:05-757586 DEBUG    Extensions all: []
20:02:05-758584 INFO     Extensions enabled: ['Lora', 'sd-extension-chainner', 'sd-extension-system-info',
                         'sd-webui-agent-scheduler', 'sd-webui-controlnet', 'sdnext-modernui',
                         'stable-diffusion-webui-images-browser', 'stable-diffusion-webui-rembg']
20:02:05-760579 INFO     Verifying requirements
20:02:05-761576 DEBUG    Setup complete without errors: 1725469326
20:02:05-775539 DEBUG    Extension preload: {'extensions-builtin': 0.01, 'extensions': 0.0}
20:02:05-777534 DEBUG    Starting module: <module 'webui' from 'c:\\ai\\automatic\\webui.py'>
20:02:05-778532 INFO     Command line args: ['--medvram', '--debug'] medvram=True debug=True
20:02:05-780526 DEBUG    Env flags: ['SD_LOAD_DEBUG=true']
20:02:17-357715 INFO     Load packages: {'torch': '2.4.0+cu124', 'diffusers': '0.31.0.dev0', 'gradio': '3.43.2'}
20:02:18-996830 DEBUG    Read: file="config.json" json=35 bytes=1517 time=0.000
20:02:18-998568 DEBUG    Unknown settings: ['cross_attention_options']
20:02:19-001904 INFO     Engine: backend=Backend.DIFFUSERS compute=cuda device=cuda attention="Scaled-Dot-Product"
                         mode=no_grad
20:02:19-055515 INFO     Device: device=NVIDIA GeForce RTX 4080 n=1 arch=sm_90 cap=(8, 9) cuda=12.4 cudnn=90100
                         driver=560.81
20:02:19-058507 DEBUG    Read: file="html\reference.json" json=52 bytes=29118 time=0.001
20:02:19-987373 DEBUG    ONNX: version=1.19.0 provider=CUDAExecutionProvider, available=['AzureExecutionProvider',
                         'CPUExecutionProvider']
20:02:20-350784 DEBUG    Importing LDM
20:02:20-384132 DEBUG    Entering start sequence
20:02:20-387596 DEBUG    Initializing
20:02:20-444498 INFO     Available VAEs: path="models\VAE" items=0
20:02:20-446465 DEBUG    Available UNets: path="models\UNET" items=0
20:02:20-448082 DEBUG    Available T5s: path="models\T5" items=0
20:02:20-449079 INFO     Disabled extensions: ['sd-webui-controlnet', 'sdnext-modernui']
20:02:20-452072 DEBUG    Read: file="cache.json" json=2 bytes=10089 time=0.001
20:02:20-459052 DEBUG    Read: file="metadata.json" json=559 bytes=1861768 time=0.006
20:02:20-465125 DEBUG    Scanning diffusers cache: folder=models\Diffusers items=2 time=0.00
20:02:20-467002 INFO     Available models: path="models\Stable-diffusion" items=21 time=0.02
20:02:21-156128 DEBUG    Load extensions
20:02:21-253129 INFO     Extension: script='extensions-builtin\Lora\scripts\lora_script.py'
                         [2;36m20:02:21-247351[0m[2;36m [0m[34mINFO    [0m LoRA networks: [33mavailable[0m=[1;36m70[0m
                         [33mfolders[0m=[1;36m2[0m
20:02:22-040634 INFO     Extension: script='extensions-builtin\sd-webui-agent-scheduler\scripts\task_scheduler.py' Using
                         sqlite file: extensions-builtin\sd-webui-agent-scheduler\task_scheduler.sqlite3
20:02:22-313218 DEBUG    Extensions init time: 1.16 sd-extension-chainner=0.07 sd-webui-agent-scheduler=0.70
                         stable-diffusion-webui-images-browser=0.25
20:02:22-345963 DEBUG    Read: file="html/upscalers.json" json=4 bytes=2672 time=0.000
20:02:22-347236 DEBUG    Read: file="extensions-builtin\sd-extension-chainner\models.json" json=24 bytes=2719 time=0.000
20:02:22-350230 DEBUG    chaiNNer models: path="models\chaiNNer" defined=24 discovered=0 downloaded=8
20:02:22-352225 DEBUG    Upscaler type=ESRGAN folder="models\ESRGAN" model="1x-ITF-SkinDiffDetail-Lite-v1"
                         path="models\ESRGAN\1x-ITF-SkinDiffDetail-Lite-v1.pth"
20:02:22-353222 DEBUG    Upscaler type=ESRGAN folder="models\ESRGAN" model="4xNMKDSuperscale_4xNMKDSuperscale"
                         path="models\ESRGAN\4xNMKDSuperscale_4xNMKDSuperscale.pth"
20:02:22-354219 DEBUG    Upscaler type=ESRGAN folder="models\ESRGAN" model="4x_NMKD-Siax_200k"
                         path="models\ESRGAN\4x_NMKD-Siax_200k.pth"
20:02:22-358208 DEBUG    Load upscalers: total=56 downloaded=11 user=3 time=0.04 ['None', 'Lanczos', 'Nearest',
                         'ChaiNNer', 'AuraSR', 'ESRGAN', 'LDSR', 'RealESRGAN', 'SCUNet', 'SD', 'SwinIR']
20:02:22-375395 DEBUG    Load styles: folder="models\styles" items=288 time=0.02
20:02:22-381407 DEBUG    Creating UI
20:02:22-382451 DEBUG    UI themes available: type=Standard themes=12
20:02:22-384449 INFO     UI theme: type=Standard name="black-teal"
20:02:22-391430 DEBUG    UI theme: css="C:\ai\automatic\javascript\black-teal.css" base="sdnext.css" user="None"
20:02:22-395007 DEBUG    UI initialize: txt2img
20:02:22-455846 DEBUG    Networks: page='model' items=72 subfolders=2 tab=txt2img folders=['models\\Stable-diffusion',
                         'models\\Diffusers', 'models\\Reference'] list=0.04 thumb=0.01 desc=0.00 info=0.00 workers=4
                         sort=Default
20:02:22-464822 DEBUG    Networks: page='lora' items=70 subfolders=0 tab=txt2img folders=['models\\Lora',
                         'models\\LyCORIS'] list=0.04 thumb=0.01 desc=0.02 info=0.03 workers=4 sort=Default
20:02:22-495740 DEBUG    Networks: page='style' items=288 subfolders=1 tab=txt2img folders=['models\\styles', 'html']
                         list=0.04 thumb=0.00 desc=0.00 info=0.00 workers=4 sort=Default
20:02:22-500263 DEBUG    Networks: page='embedding' items=13 subfolders=0 tab=txt2img folders=['models\\embeddings']
                         list=0.03 thumb=0.01 desc=0.00 info=0.00 workers=4 sort=Default
20:02:22-502258 DEBUG    Networks: page='vae' items=0 subfolders=0 tab=txt2img folders=['models\\VAE'] list=0.00
                         thumb=0.00 desc=0.00 info=0.00 workers=4 sort=Default
20:02:22-584040 DEBUG    UI initialize: img2img
20:02:22-841086 DEBUG    UI initialize: control models=models\control
20:02:23-117801 DEBUG    Read: file="ui-config.json" json=0 bytes=2 time=0.000
20:02:23-220723 DEBUG    UI themes available: type=Standard themes=12
20:02:23-788205 DEBUG    Reading failed: C:\ai\automatic\html\extensions.json [Errno 2] No such file or directory:
                         'C:\\ai\\automatic\\html\\extensions.json'
20:02:23-790756 INFO     Extension list is empty: refresh required
20:02:24-380172 DEBUG    Extension list: processed=8 installed=8 enabled=6 disabled=2 visible=8 hidden=0
20:02:24-733069 DEBUG    Root paths: ['c:\\ai\\automatic']
20:02:24-843958 INFO     Local URL: http://127.0.0.1:7860/
20:02:24-844955 DEBUG    Gradio functions: registered=2366
20:02:24-847946 DEBUG    FastAPI middleware: ['Middleware', 'Middleware']
20:02:24-850939 DEBUG    Creating API
20:02:25-018490 INFO     [AgentScheduler] Task queue is empty
20:02:25-020487 INFO     [AgentScheduler] Registering APIs
20:02:25-146150 DEBUG    Scripts setup: ['IP Adapters:0.022', 'AnimateDiff:0.007', 'CogVideoX:0.006', 'X/Y/Z
                         Grid:0.169', 'Face:0.012', 'Image-to-Video:0.007']
20:02:25-147147 DEBUG    Model metadata: file="metadata.json" no changes
20:02:25-148145 DEBUG    Torch mode: deterministic=False
20:02:25-176069 INFO     Torch override VAE dtype: no-half set
20:02:25-177068 DEBUG    Desired Torch parameters: dtype=FP16 no-half=False no-half-vae=True upscast=False
20:02:25-178065 INFO     Setting Torch parameters: device=cuda dtype=torch.float16 vae=torch.float32 unet=torch.float16
                         context=no_grad fp16=True bf16=None optimization=Scaled-Dot-Product
20:02:25-180059 DEBUG    Model requested: fn=<lambda>
20:02:25-181057 INFO     Select: model="Diffusers\Disty0/FLUX.1-dev-qint4 [82811df42b]"
20:02:25-182054 DEBUG    Load model: existing=False
                         target=models\Diffusers\models--Disty0--FLUX.1-dev-qint4\snapshots\82811df42b556a1153b971d8375d
                         5170c306a6eb info=None
20:02:25-183051 DEBUG    Diffusers loading:
                         path="models\Diffusers\models--Disty0--FLUX.1-dev-qint4\snapshots\82811df42b556a1153b971d8375d5
                         170c306a6eb"
20:02:25-185045 INFO     Autodetect: model="FLUX" class=FluxPipeline
                         file="models\Diffusers\models--Disty0--FLUX.1-dev-qint4\snapshots\82811df42b556a1153b971d8375d5
                         170c306a6eb" size=0MB
20:02:25-194021 DEBUG    Loading FLUX: model="Diffusers\Disty0/FLUX.1-dev-qint4" repo="Disty0/FLUX.1-dev-qint4"
                         unet="None" t5="None" vae="None" quant=qint4 offload=model dtype=torch.float16
20:02:25-195018 TRACE    Loading FLUX: config={'low_cpu_mem_usage': True, 'torch_dtype': torch.float16,
                         'load_connected_pipeline': True, 'safety_checker': None, 'requires_safety_checker': False}
20:02:25-713291 TRACE    Loading FLUX: quantization
                         map="models\Diffusers\models--Disty0--FLUX.1-dev-qint4\snapshots\82811df42b556a1153b971d8375d51
                         70c306a6eb\transformer\quantization_map.json" repo="Diffusers\Disty0/FLUX.1-dev-qint4"
                         component="transformer"
transformer/quantization_map.json: 100%|███████████████████████████████████████████| 42.9k/42.9k [00:00<00:00, 345kB/s]
20:03:58-111204 ERROR    Loading FLUX: Failed to cast transformer to torch.float16, set dtype to torch.bfloat16
20:03:58-112201 TRACE    Loading FLUX: quantization
                         map="models\Diffusers\models--Disty0--FLUX.1-dev-qint4\snapshots\82811df42b556a1153b971d8375d51
                         70c306a6eb\text_encoder_2\quantization_map.json" repo="Diffusers\Disty0/FLUX.1-dev-qint4"
                         component="text_encoder_2"
text_encoder_2/quantization_map.json: 100%|███████████████████████████████████████████████| 15.1k/15.1k [00:00<?, ?B/s]
20:04:38-563559 ERROR    Loading FLUX: Failed to cast text encoder to torch.float16, set dtype to torch.float16
20:04:38-565551 DEBUG    Loading FLUX: preloaded=['transformer', 'text_encoder_2']
Loading pipeline components... 100% ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 7/7  [ 0:00:00 < 0:00:00 , 4 C/s ]
20:04:40-130008 INFO     Load embeddings: loaded=0 skipped=13 time=0.02
20:04:40-207139 DEBUG    Setting model VAE: no-half=True
20:04:40-208135 DEBUG    Setting model: slicing=True
20:04:40-210129 DEBUG    Setting model: tiling=True
20:04:40-210129 DEBUG    Setting model: attention=Scaled-Dot-Product
20:04:40-229080 DEBUG    Setting model: offload=model
20:04:40-752365 DEBUG    GC: utilization={'gpu': 8, 'ram': 31, 'threshold': 80} gc={'collected': 561, 'saved': 0.0}
                         before={'gpu': 1.33, 'ram': 19.59} after={'gpu': 1.33, 'ram': 19.59, 'retries': 0, 'oom': 0}
                         device=cuda fn=load_diffuser time=0.21
20:04:40-754332 INFO     Load model: time=135.36 load=134.92 options=0.10 move=0.31 native=1024 {'ram': {'used': 19.59,
                         'total': 63.92}, 'gpu': {'used': 1.33, 'total': 15.99}, 'retries': 0, 'oom': 0}
20:04:40-757324 DEBUG    Script callback init time: image_browser.py:ui_tabs=0.42 system-info.py:app_started=0.06
                         task_scheduler.py:app_started=0.14
20:04:40-759319 INFO     Startup time: 154.97 torch=7.64 gradio=2.20 diffusers=1.73 libraries=2.99 samplers=0.06
                         extensions=1.16 face-restore=0.69 ui-en=0.22 ui-txt2img=0.06 ui-img2img=0.22 ui-control=0.12
                         ui-settings=0.24 ui-extensions=1.05 ui-defaults=0.27 launch=0.17 api=0.09 app-started=0.20
                         checkpoint=135.61
20:04:40-760316 DEBUG    Save: file="config.json" json=35 bytes=1408 time=0.003
20:04:40-763307 DEBUG    Unused settings: ['cross_attention_options']
20:04:52-713683 INFO     MOTD: N/A
20:04:55-273269 DEBUG    UI themes available: type=Standard themes=12
20:04:55-487899 INFO     Browser session: user=None client=127.0.0.1 agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64)
                         AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36 Edg/128.0.0.0
20:05:12-395501 INFO     Base: class=FluxPipeline
20:05:12-397496 DEBUG    Sampler default FlowMatchEulerDiscreteScheduler: {'num_train_timesteps': 1000, 'shift': 3.0,
                         'use_dynamic_shifting': True, 'base_shift': 0.5, 'max_shift': 1.15, 'base_image_seq_len': 256,
                         'max_image_seq_len': 4096}
20:05:12-416445 DEBUG    Torch generator: device=cuda seeds=[2753494145]
20:05:12-417443 DEBUG    Diffuser pipeline: FluxPipeline task=DiffusersTaskType.TEXT_2_IMAGE batch=1/1x1 set={'prompt':
                         1, 'guidance_scale': 6, 'num_inference_steps': 20, 'output_type': 'latent', 'width': 1024,
                         'height': 1024, 'parser': 'Fixed attention'}
Progress ?it/s                                              0% 0/20 00:03 ? Base
20:05:18-541098 ERROR    Processing: args={'prompt': ['photo of a woman'], 'guidance_scale': 6, 'generator':
                         [<torch._C.Generator object at 0x000001D50D2C9C70>], 'callback_on_step_end': <function
                         diffusers_callback at 0x000001D50D84F880>, 'callback_on_step_end_tensor_inputs': ['latents'],
                         'num_inference_steps': 20, 'output_type': 'latent', 'width': 1024, 'height': 1024} expected
                         mat1 and mat2 to have the same dtype, but got: struct c10::Half != struct c10::BFloat16
20:05:18-543095 ERROR    Processing: RuntimeError
╭───────────────────────────────────────── Traceback (most recent call last) ──────────────────────────────────────────╮
│ C:\ai\automatic\modules\processing_diffusers.py:122 in process_diffusers                                             │
│                                                                                                                      │
│   121 │   │   else:                                                                                                  │
│ ❱ 122 │   │   │   output = shared.sd_model(**base_args)                                                              │
│   123 │   │   if isinstance(output, dict):                                                                           │
│                                                                                                                      │
│ c:\ai\automatic\venv\Lib\site-packages\torch\utils\_contextlib.py:116 in decorate_context                            │
│                                                                                                                      │
│   115 │   │   with ctx_factory():                                                                                    │
│ ❱ 116 │   │   │   return func(*args, **kwargs)                                                                       │
│   117                                                                                                                │
│                                                                                                                      │
│ c:\ai\automatic\venv\Lib\site-packages\diffusers\pipelines\flux\pipeline_flux.py:719 in __call__                     │
│                                                                                                                      │
│   718 │   │   │   │                                                                                                  │
│ ❱ 719 │   │   │   │   noise_pred = self.transformer(                                                                 │
│   720 │   │   │   │   │   hidden_states=latents,                                                                     │
│                                                                                                                      │
│ c:\ai\automatic\venv\Lib\site-packages\torch\nn\modules\module.py:1553 in _wrapped_call_impl                         │
│                                                                                                                      │
│   1552 │   │   else:                                                                                                 │
│ ❱ 1553 │   │   │   return self._call_impl(*args, **kwargs)                                                           │
│   1554                                                                                                               │
│                                                                                                                      │
│ c:\ai\automatic\venv\Lib\site-packages\torch\nn\modules\module.py:1562 in _call_impl                                 │
│                                                                                                                      │
│   1561 │   │   │   │   or _global_forward_hooks or _global_forward_pre_hooks):                                       │
│ ❱ 1562 │   │   │   return forward_call(*args, **kwargs)                                                              │
│   1563                                                                                                               │
│                                                                                                                      │
│                                               ... 4 frames hidden ...                                                │
│                                                                                                                      │
│ c:\ai\automatic\venv\Lib\site-packages\optimum\quanto\nn\qlinear.py:45 in forward                                    │
│                                                                                                                      │
│   44 │   def forward(self, input: torch.Tensor) -> torch.Tensor:                                                     │
│ ❱ 45 │   │   return torch.nn.functional.linear(input, self.qweight, bias=self.bias)                                  │
│   46                                                                                                                 │
│                                                                                                                      │
│ c:\ai\automatic\venv\Lib\site-packages\optimum\quanto\tensor\qtensor.py:90 in __torch_function__                     │
│                                                                                                                      │
│   89 │   │   if qfunc is not None:                                                                                   │
│ ❱ 90 │   │   │   return qfunc(*args, **kwargs)                                                                       │
│   91 │   │   # Defer to dispatcher to look instead for QTensor subclasses operations                                 │
│                                                                                                                      │
│ c:\ai\automatic\venv\Lib\site-packages\optimum\quanto\tensor\qtensor_func.py:152 in linear                           │
│                                                                                                                      │
│   151 def linear(func, input, other, bias=None):                                                                     │
│ ❱ 152 │   return QTensorLinear.apply(input, other, bias)                                                             │
│   153                                                                                                                │
│                                                                                                                      │
│ c:\ai\automatic\venv\Lib\site-packages\torch\autograd\function.py:574 in apply                                       │
│                                                                                                                      │
│   573 │   │   │   args = _functorch.utils.unwrap_dead_wrappers(args)                                                 │
│ ❱ 574 │   │   │   return super().apply(*args, **kwargs)  # type: ignore[misc]                                        │
│   575                                                                                                                │
│                                                                                                                      │
│ c:\ai\automatic\venv\Lib\site-packages\optimum\quanto\tensor\qtensor_func.py:128 in forward                          │
│                                                                                                                      │
│   127 │   │   else:                                                                                                  │
│ ❱ 128 │   │   │   output = torch.matmul(input, other.t())                                                            │
│   129 │   │   if bias is not None:                                                                                   │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
RuntimeError: expected mat1 and mat2 to have the same dtype, but got: struct c10::Half != struct c10::BFloat16
20:05:18-810519 INFO     Processed: images=0 time=6.43 its=0.00 memory={'ram': {'used': 15.07, 'total': 63.92}, 'gpu':
                         {'used': 7.68, 'total': 15.99}, 'retries': 0, 'oom': 0}

ok, this seems near the finish line

20:03:58-111204 ERROR Loading FLUX: Failed to cast transformer to torch.float16, set dtype to torch.bfloat16

i need to figure out fp16 vs bf16 internally, for now set settings -> compute -> device precision > bf16

I have no idea what comment they've deleted, I haven't made any further comment

i think it was a previous comment related to when user posted a malicious download link that i've removed and flagged

ok, this seems near the finish line

20:03:58-111204 ERROR Loading FLUX: Failed to cast transformer to torch.float16, set dtype to torch.bfloat16

i need to figure out fp16 vs bf16 internally, for now set settings -> compute -> device precision > bf16

Thank you, it works now and I can run generations. I just need to remember to switch back to fp16 when using normal SDXL models.

Is 1.66s/it normal on a 4080? It is not running out of VRAM. Seems significantly slower than your benchmark. Should I open a separate issue?

07:22:21-429561 DEBUG    Sampler default FlowMatchEulerDiscreteScheduler: {'num_train_timesteps': 1000, 'shift': 3.0,
                         'use_dynamic_shifting': True, 'base_shift': 0.5, 'max_shift': 1.15, 'base_image_seq_len': 256,
                         'max_image_seq_len': 4096}
07:22:21-454494 DEBUG    Torch generator: device=cuda seeds=[3330659293]
07:22:21-455490 DEBUG    Diffuser pipeline: FluxPipeline task=DiffusersTaskType.TEXT_2_IMAGE batch=1/1x1 set={'prompt':
                         1, 'guidance_scale': 6, 'num_inference_steps': 30, 'output_type': 'latent', 'width': 1024,
                         'height': 1024, 'parser': 'Fixed attention'}
Progress  2.64s/it ██▎                                  7% 2/30 00:05 01:13 Base07:22:29-043639 DEBUG    VAE load: type=taesd model=models\TAESD\taef1_decoder.pth
Progress  1.66s/it █████████████████████████████████ 100% 30/30 00:49 00:00 Base
07:23:19-089701 INFO     Processed: images=1 time=57.68 its=0.52 memory={'ram': {'used': 12.33, 'total': 63.92}, 'gpu':
                         {'used': 2.4, 'total': 15.99}, 'retries': 0, 'oom': 0}

its within expected range, my numbers were for rtx4090.

I just need to remember to switch back to fp16 when using normal SDXL models.

why? what's wrong with just leaving bf16?

why? what's wrong with just leaving bf16?

For inference I don't know the difference / could not compare results, but training with bf16 yielded lower quality / worse than training with fp16.

vladmandic / automatic