producing only black images

[YabbaYabbaYabba]

Installed but every image is just a black square

[0xbitches]

Does the console output an error message? There is too little information for me to help.

[YabbaYabbaYabba]

Does the console output an error message? There is too little information for me to help.

Ooops.. silly me. Sorry about that , I did copy paste but it did not save.

I;m running on Manjaro Linux, GPU is AMD 6700XT (12Gb) RAM: 64Gb

command line starting with : ./webui.sh --disable-nan-check

################################################################ Install script for stable-diffusion + Web UI Tested on Debian 11 (Bullseye) ################################################################

################################################################ Running on dr user ################################################################

################################################################ Repo already cloned, using it as install directory ################################################################

################################################################ Create and activate python venv ################################################################

################################################################ Launching launch.py... ################################################################ Using TCMalloc: libtcmalloc_minimal.so.4 Python 3.11.5 (main, Sep 2 2023, 14:16:33) [GCC 13.2.1 20230801] Version: v1.6.0 Commit hash: 5ef669de080814067961f28357256e8fe27544f4 Installing requirements Installing sd-webui-controlnet requirement: changing opencv-python version from 4.7.0.72 to 4.8.0 Checking roop requirements Install insightface==0.7.3 Installing sd-webui-roop requirement: insightface==0.7.3 Install onnx==1.14.0 Installing sd-webui-roop requirement: onnx==1.14.0 Install onnxruntime==1.15.0 Installing sd-webui-roop requirement: onnxruntime==1.15.0 Install opencv-python==4.7.0.72 Installing sd-webui-roop requirement: opencv-python==4.7.0.72 Launching Web UI with arguments: --disable-nan-check --upcast-sampling --opt-sub-quad-attention --no-half-vae no module 'xformers'. Processing without... no module 'xformers'. Processing without... No module 'xformers'. Proceeding without it. Civitai Helper: Get Custom Model Folder Civitai Helper: Load setting from: /home/dr/sdxl/stable-diffusion-webui/stable-diffusion-webui/extensions/Stable-Diffusion-Webui-Civitai-Helper/setting.json Civitai Helper: No setting file, use default [-] ADetailer initialized. version: 23.10.1, num models: 9 2023-10-23 10:53:11,657 - ControlNet - INFO - ControlNet v1.1.411 ControlNet preprocessor location: /home/dr/sdxl/stable-diffusion-webui/stable-diffusion-webui/extensions/sd-webui-controlnet/annotator/downloads 2023-10-23 10:53:11,705 - ControlNet - INFO - ControlNet v1.1.411 Loading pipeline components...: 17%|██████████████▌ | 1/6 [00:00<00:01, 4.76it/s] * Error loading script: main.py Traceback (most recent call last): File "/home/dr/sdxl/stable-diffusion-webui/stable-diffusion-webui/modules/scripts.py", line 382, in load_scripts script_module = script_loading.load_module(scriptfile.path) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/dr/sdxl/stable-diffusion-webui/stable-diffusion-webui/modules/script_loading.py", line 10, in load_module module_spec.loader.exec_module(module) File "", line 940, in exec_module File "", line 241, in _call_with_frames_removed File "/home/dr/sdxl/stable-diffusion-webui/stable-diffusion-webui/extensions/sd-webui-lcm/scripts/main.py", line 71, in pipe = LatentConsistencyModelPipeline.from_pretrained( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/dr/sdxl/stable-diffusion-webui/stable-diffusion-webui/venv/lib/python3.11/site-packages/diffusers/pipelines/pipeline_utils.py", line 1105, in from_pretrained loaded_sub_model = load_sub_model( ^^^^^^^^^^^^^^^ File "/home/dr/sdxl/stable-diffusion-webui/stable-diffusion-webui/venv/lib/python3.11/site-packages/diffusers/pipelines/pipeline_utils.py", line 472, in load_sub_model loaded_sub_model = load_method(os.path.join(cached_folder, name), loading_kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/dr/sdxl/stable-diffusion-webui/stable-diffusion-webui/venv/lib/python3.11/site-packages/transformers/tokenization_utils_base.py", line 1825, in from_pretrained return cls._from_pretrained( ^^^^^^^^^^^^^^^^^^^^^ File "/home/dr/sdxl/stable-diffusion-webui/stable-diffusion-webui/venv/lib/python3.11/site-packages/transformers/tokenization_utils_base.py", line 2044, in _from_pretrained raise ValueError( ValueError: Non-consecutive added token '<|startoftext|>' found. Should have index 49408 but has index 49406 in saved vocabulary.

---

2023-10-23 10:53:12,400 - roop - INFO - roop v0.0.2-uncensored 2023-10-23 10:53:12,401 - roop - INFO - roop v0.0.2-uncensored Loading weights [84feab3a32] from /home/dr/sdxl/stable-diffusion-webui/stable-diffusion-webui/models/Stable-diffusion/LCM_Dreamshaper_v7_4k.safetensors Running on local URL: http://127.0.0.1:7860 Creating model from config: /home/dr/sdxl/stable-diffusion-webui/stable-diffusion-webui/configs/v1-inference.yaml

To create a public link, set share=True in launch(). Startup time: 30.6s (prepare environment: 24.5s, import torch: 2.3s, import gradio: 0.4s, setup paths: 0.4s, other imports: 0.4s, load scripts: 1.8s, create ui: 0.5s, gradio launch: 0.2s). Applying attention optimization: sub-quadratic... done. Model loaded in 2.2s (load weights from disk: 0.5s, create model: 1.1s, apply half(): 0.2s, calculate empty prompt: 0.2s).

There when running model : Model loaded in 2.2s (load weights from disk: 0.5s, create model: 1.1s, apply half(): 0.2s, calculate empty prompt: 0.2s). 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 30/30 [00:06<00:00, 4.62it/s] /home/dr/sdxl/stable-diffusion-webui/stable-diffusion-webui/modules/processing.py:906: RuntimeWarning: invalid value encountered in cast0, 4.66it/s] x_sample = x_sample.astype(np.uint8) Total progress: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████| 30/30 [00:06<00:00, 4.55it/s] Total progress: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████| 30/30 [00:06<00:00, 4.66it/s]

[0xbitches]

Looks like LCM did not load properly due to a known issue: ValueError: Non-consecutive added token '<|startoftext|>' found. Should have index 49408 but has index 49406 in saved vocabulary. Please refer to https://github.com/0xbitches/sd-webui-lcm#known-issues for a detailed solution.

After fixing the .json file, you should see a dedicated LCM tab.

[YabbaYabbaYabba]

Sorry i know you closed this as resolved.

I just cant find provided solution path or files. Search found nothing. Closest I've found is /home/user/sdxl/stable-diffusion-webui/stable-diffusion-webui/venv/lib/python3.11/site-packages/huggingface_hub/ but no added_tokens.json. file

Does anyone have any idea where this should be on Linux?

[0xbitches]

It should be under ~/.cache/ on linux. The path you provided is the path to the huggingface hub package itself, not the path to the model caches.

Try running ls ~/.cache/ or echo $HF_HOME

[YabbaYabbaYabba]

Thank you, will check that . Very excited to get this working :)

[YabbaYabbaYabba]

found it in : ~/.cache/huggingface/hub/models--SimianLuo--LCM_Dreamshaper_v7/snapshots/c7f9b672c65a664af57d1de926819fd79cb26eb8/tokenizer/added_tokens.json

Thank you for your help, really appreciated !

Very fast!!!!

Applying attention optimization: sub-quadratic... done. Model loaded in 2.0s (load weights from disk: 0.6s, create model: 1.0s, apply half(): 0.1s, calculate empty prompt: 0.2s). LCM inference time: 0.5817761421203613 seconds LCM inference time: 0.8696818351745605 seconds LCM inference time: 0.8814699649810791 seconds LCM inference time: 0.8761799335479736 seconds LCM inference time: 0.8719279766082764 seconds LCM inference time: 2.6093060970306396 seconds LCM inference time: 2.518545150756836 seconds LCM inference time: 2.5358474254608154 seconds LCM inference time: 2.543264150619507 seconds

[sumeetprashant]

I had a similar issue first images were black, now they are just noise and for some reason my folder here

C:\Users\User Name.cache\huggingface\hub\models--SimianLuo--LCM_Dreamshaper_v7\snapshots \c255dc8f16c927b2a6af52092a5ec17903b3a24a\tokenizer

doesn't have the added_token.json file

I have checked with VAE and without VAE, this issue persists.