[X] The issue exists after disabling all extensions
[X] The issue exists on a clean installation of webui
[ ] The issue is caused by an extension, but I believe it is caused by a bug in the webui
[X] The issue exists in the current version of the webui
[X] The issue has not been reported before recently
[ ] The issue has been reported before but has not been fixed yet
What happened?
controlnet integrated preprocessor tile_resample and model control_v11f1e_sd15_tile [a371b31b] i couldn't turn on down sampling and i couldn't find the bar of down sampling control
Steps to reproduce the problem
1- enable controlnet integrated preprocessor tile_resample and model control_v11f1e_sd15_tile [a371b31b]
What should have happened?
its should show down sample bar to control the down sampling rate
like in A1111
Already up to date.
venv "C:\Users\Admin\webui_forge_cu121_torch21\webui\venv\Scripts\Python.exe"
Python 3.10.11 (tags/v3.10.11:7d4cc5a, Apr 5 2023, 00:38:17) [MSC v.1929 64 bit (AMD64)]
Version: f0.0.17v1.8.0rc-latest-276-g29be1da7
Commit hash: 29be1da7cf2b5dccfc70fbdd33eb35c56a31ffb7
#######################################################################################################
Initializing Civitai Link
If submitting an issue on github, please provide the below text for debugging purposes:
Python revision: 3.10.11 (tags/v3.10.11:7d4cc5a, Apr 5 2023, 00:38:17) [MSC v.1929 64 bit (AMD64)]
Civitai Link revision: 115cd9c35b0774c90cb9c397ad60ef6a7dac60de
SD-WebUI revision: 29be1da7cf2b5dccfc70fbdd33eb35c56a31ffb7
Checking Civitai Link requirements...
#######################################################################################################
Launching Web UI with arguments: --skip-torch-cuda-test --precision full --no-half --always-cpu --autolaunch
Total VRAM 12237 MB, total RAM 12237 MB
Set vram state to: DISABLED
Device: cpu
VAE dtype: torch.float32
C:\Users\Admin\webui_forge_cu121_torch21\webui\venv\lib\site-packages\torch\cuda\__init__.py:138: UserWarning: CUDA initialization: The NVIDIA driver on your system is too old (found version 9010). Please update your GPU driver by downloading and installing a new version from the URL: http://www.nvidia.com/Download/index.aspx Alternatively, go to: https://pytorch.org to install a PyTorch version that has been compiled with your version of the CUDA driver. (Triggered internally at ..\c10\cuda\CUDAFunctions.cpp:108.)
return torch._C._cuda_getDeviceCount() > 0
CUDA Stream Activated: False
Warning: caught exception 'The NVIDIA driver on your system is too old (found version 9010). Please update your GPU driver by downloading and installing a new version from the URL: http://www.nvidia.com/Download/index.aspx Alternatively, go to: https://pytorch.org to install a PyTorch version that has been compiled with your version of the CUDA driver.', memory monitor disabled
Using sub quadratic optimization for cross attention, if you have memory or speed issues try using: --attention-split
ControlNet preprocessor location: C:\Users\Admin\webui_forge_cu121_torch21\webui\models\ControlNetPreprocessor
CHv1.8.5: Get Custom Model Folder
Tag Autocomplete: Could not locate model-keyword extension, Lora trigger word completion will be limited to those added through the extra networks menu.
[-] ADetailer initialized. version: 24.4.2, num models: 18
20:48:32 - ReActor - STATUS - Running v0.7.0-b7 on Device: CPU
Civitai: API loaded
Loading weights [e73d775ff9] from C:\Users\Admin\webui_forge_cu121_torch21\webui\models\Stable-diffusion\theTrualityEngine_trualityENGINEPRO.safetensors
model_type EPS
UNet ADM Dimension 0
2024-04-27 20:48:37,653 - ControlNet - INFO - ControlNet UI callback registered.
CHv1.8.5: Set Proxy:
Running on local URL: http://127.0.0.1:7860
To create a public link, set `share=True` in `launch()`.
Civitai: Check resources for missing info files
Civitai: Check resources for missing preview images
Startup time: 53.7s (prepare environment: 18.8s, import torch: 8.6s, import gradio: 2.7s, setup paths: 2.9s, initialize shared: 1.3s, other imports: 1.6s, list SD models: 1.0s, load scripts: 10.3s, scripts list_optimizers: 0.1s, create ui: 4.3s, gradio launch: 2.0s).
Civitai: Found 0 resources missing info files
Civitai: No info found on Civitai
Civitai: Found 7 resources missing preview images
Civitai: No preview images found on Civitai
Using split attention in VAE
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
Using split attention in VAE
extra {'cond_stage_model.clip_l.text_projection', 'cond_stage_model.clip_l.logit_scale'}
left over keys: dict_keys(['model_ema.decay', 'model_ema.num_updates'])
Loading VAE weights specified in settings: C:\Users\Admin\webui_forge_cu121_torch21\webui\models\VAE\vae-ft-mse-840000-ema-pruned_fp16.pt
To load target model SD1ClipModel
Begin to load 1 model
Moving model(s) has taken 0.01 seconds
Model loaded in 42.0s (load weights from disk: 0.7s, forge load real models: 32.5s, load VAE: 3.2s, load textual inversion embeddings: 4.4s, calculate empty prompt: 1.1s).
2024-04-27 20:57:35,009 - ControlNet - INFO - Preview Resolution = 0.5
Canva size: 1024x1536
Image size: 512x768
Scale factor: 2
Upscaling iteration 1 with scale factor 2
Cleanup minimal inference memory.
tiled upscale: 100%|███████████████████████████████████████████████| 15/15 [04:13<00:00, 16.91s/it]
Tile size: 512x512
Tiles amount: 6
Grid: 3x2
Redraw enabled: True
Seams fix mode: NONE
2024-04-27 21:03:40,804 - ControlNet - INFO - ControlNet Input Mode: InputMode.SIMPLE
2024-04-27 21:03:40,809 - ControlNet - INFO - Crop input image based on A1111 mask.
2024-04-27 21:03:41,003 - ControlNet - INFO - Using preprocessor: tile_resample
2024-04-27 21:03:41,003 - ControlNet - INFO - preprocessor resolution = 0.5
Warning torch.load doesn't support weights_only on this pytorch version, loading unsafely.
[] []
2024-04-27 21:03:45,720 - ControlNet - INFO - Current ControlNet ControlNetPatcher: C:\Users\Admin\webui_forge_cu121_torch21\webui\models\ControlNet\control_v11f1e_sd15_tile.pth
NeverOOM Enabled for UNet (always maximize offload)
NeverOOM Enabled for VAE (always tiled)
VARM State Changed To NO_VRAM
To load target model AutoencoderKL
Begin to load 1 model
Moving model(s) has taken 0.02 seconds
VAE tiled encode: 100%|████████████████████████████████████████████| 10/10 [00:48<00:00, 4.86s/it]
[LORA] Loaded C:\Users\Admin\webui_forge_cu121_torch21\webui\models\Lora\beltbra_v0.1.safetensors for BaseModel-UNet with 192 keys at weight 1.0 (skipped 0 keys)
[LORA] Loaded C:\Users\Admin\webui_forge_cu121_torch21\webui\models\Lora\beltbra_v0.1.safetensors for BaseModel-CLIP with 72 keys at weight 1.0 (skipped 0 keys)
[LORA] Loaded C:\Users\Admin\webui_forge_cu121_torch21\webui\models\Lora\ExtremeMicroShorts.safetensors for BaseModel-UNet with 192 keys at weight 0.8 (skipped 0 keys)
[LORA] Loaded C:\Users\Admin\webui_forge_cu121_torch21\webui\models\Lora\ExtremeMicroShorts.safetensors for BaseModel-CLIP with 72 keys at weight 0.8 (skipped 0 keys)
[LORA] Loaded C:\Users\Admin\webui_forge_cu121_torch21\webui\models\Lora\Nixmare-15.safetensors for BaseModel-UNet with 192 keys at weight 0.5 (skipped 0 keys)
[LORA] Loaded C:\Users\Admin\webui_forge_cu121_torch21\webui\models\Lora\Nixmare-15.safetensors for BaseModel-CLIP with 72 keys at weight 0.5 (skipped 0 keys)
[LORA] Loaded C:\Users\Admin\webui_forge_cu121_torch21\webui\models\Lora\Verotika-Xstar-v7.safetensors for BaseModel-UNet with 192 keys at weight 0.4 (skipped 0 keys)
[LORA] Loaded C:\Users\Admin\webui_forge_cu121_torch21\webui\models\Lora\Verotika-Xstar-v7.safetensors for BaseModel-CLIP with 72 keys at weight 0.4 (skipped 0 keys)
[LORA] Loaded C:\Users\Admin\webui_forge_cu121_torch21\webui\models\Lora\GoodHands-beta2.safetensors for BaseModel-UNet with 278 keys at weight 0.8 (skipped 0 keys)
[LORA] Loaded C:\Users\Admin\webui_forge_cu121_torch21\webui\models\Lora\GoodHands-beta2.safetensors for BaseModel-CLIP with 72 keys at weight 0.8 (skipped 0 keys)
[LORA] Loaded C:\Users\Admin\webui_forge_cu121_torch21\webui\models\Lora\HD Horizon v1_0.safetensors for BaseModel-UNet with 192 keys at weight 1.0 (skipped 0 keys)
[LORA] Loaded C:\Users\Admin\webui_forge_cu121_torch21\webui\models\Lora\HD Horizon v1_0.safetensors for BaseModel-CLIP with 72 keys at weight 1.0 (skipped 0 keys)
[LORA] Loaded C:\Users\Admin\webui_forge_cu121_torch21\webui\models\Lora\Mild detail adjusterV10_4.safetensors for BaseModel-UNet with 192 keys at weight 2.0 (skipped 0 keys)
[LORA] Loaded C:\Users\Admin\webui_forge_cu121_torch21\webui\models\Lora\Mild detail adjusterV10_4.safetensors for BaseModel-CLIP with 72 keys at weight 2.0 (skipped 0 keys)
[LORA] Loaded C:\Users\Admin\webui_forge_cu121_torch21\webui\models\Lora\AdvancedEnhancer.safetensors for BaseModel-UNet with 192 keys at weight 2.0 (skipped 0 keys)
[LORA] Loaded C:\Users\Admin\webui_forge_cu121_torch21\webui\models\Lora\AdvancedEnhancer.safetensors for BaseModel-CLIP with 72 keys at weight 2.0 (skipped 0 keys)
[LORA] Loaded C:\Users\Admin\webui_forge_cu121_torch21\webui\models\Lora\picxer_real.safetensors for BaseModel-UNet with 278 keys at weight 1.0 (skipped 0 keys)
To load target model SD1ClipModel
Begin to load 1 model
Moving model(s) has taken 6.89 seconds
2024-04-27 21:04:52,232 - ControlNet - INFO - ControlNet Method tile_resample patched.
To load target model BaseModel
To load target model ControlNet
Begin to load 2 models
Moving model(s) has taken 54.33 seconds
57%|███████████████████████████████████▏ | 21/37 [18:31<15:11, 56.94s/it]
Total progress: 9%|████ | 21/222 [17:32<2:53:36, 51.82s/it]
Checklist
What happened?
controlnet integrated preprocessor tile_resample and model control_v11f1e_sd15_tile [a371b31b] i couldn't turn on down sampling and i couldn't find the bar of down sampling control
Steps to reproduce the problem
1- enable controlnet integrated preprocessor tile_resample and model control_v11f1e_sd15_tile [a371b31b]
What should have happened?
its should show down sample bar to control the down sampling rate
like in A1111
What browsers do you use to access the UI ?
Google Chrome
Sysinfo
sysinfo-2024-04-27-18-22.json
Console logs
Additional information
using CPU only