search

AbdBarho / stable-diffusion-webui-docker

Easy Docker setup for Stable Diffusion with user-friendly UI
Other
6.67k stars 1.11k forks source link

lstein traceback and exit with error code 255 #251

Closed joshurawr closed 1 year ago

joshurawr commented 1 year ago

Has this issue been opened before?

Describe the bug

Trackback errors and exit code 255 when trying to run lstein

Which UI

Specific to lstein. Auto and hlky both function normally.

Hardware / Software

Steps to Reproduce

  1. Clean install of arch linux with nvidia 3080 and packages: nvidia-container-toolkit, nvidia, cuda, docker, docker-compose
  2. Clone repo
  3. docker compose --profile download up --build
  4. docker compose --profile lstein up --build
  5. See error below

Additional context


[+] Building 1.3s (20/20) FINISHED                                                                                                                                             
 => [internal] load build definition from Dockerfile                                                                                                                      0.0s
 => => transferring dockerfile: 32B                                                                                                                                       0.0s
 => [internal] load .dockerignore                                                                                                                                         0.0s
 => => transferring context: 2B                                                                                                                                           0.0s
 => resolve image config for docker.io/docker/dockerfile:1                                                                                                                0.6s
 => CACHED docker-image://docker.io/docker/dockerfile:1@sha256:9ba7531bd80fb0a858632727cf7a112fbfd19b17e94c4e84ced81e24ef1a0dbc                                           0.0s
 => [internal] load .dockerignore                                                                                                                                         0.0s
 => [internal] load build definition from Dockerfile                                                                                                                      0.0s
 => [internal] load metadata for docker.io/library/python:3.10-slim                                                                                                       0.3s
 => [ 1/11] FROM docker.io/library/python:3.10-slim@sha256:030ead045da5758362ae198e9025671f22490467312dbad9af6b29a6d6bc029b                                               0.0s
 => [internal] load build context                                                                                                                                         0.0s
 => => transferring context: 123B                                                                                                                                         0.0s
 => CACHED [ 2/11] RUN pip install torch==1.12.0+cu116 --extra-index-url https://download.pytorch.org/whl/cu116                                                           0.0s
 => CACHED [ 3/11] RUN apt-get update && apt-get install git -y && apt-get clean                                                                                          0.0s
 => CACHED [ 4/11] RUN git clone https://github.com/invoke-ai/InvokeAI.git /stable-diffusion                                                                              0.0s
 => CACHED [ 5/11] WORKDIR /stable-diffusion                                                                                                                              0.0s
 => CACHED [ 6/11] RUN <<EOF (git reset --hard 5c31feb3a1096d437c94b6e1c3224eb7a7224a85...)                                                                               0.0s
 => CACHED [ 7/11] RUN <<EOF (apt-get update...)                                                                                                                          0.0s
 => CACHED [ 8/11] RUN <<EOF (git fetch...)                                                                                                                               0.0s
 => CACHED [ 9/11] RUN pip install --force-reinstall opencv-python-headless && python3 -c "from patchmatch import patch_match"                                            0.0s
 => CACHED [10/11] COPY . /docker/                                                                                                                                        0.0s
 => CACHED [11/11] RUN <<EOF (python3 /docker/info.py /stable-diffusion/frontend/dist/index.html...)                                                                      0.0s
 => exporting to image                                                                                                                                                    0.1s
 => => exporting layers                                                                                                                                                   0.0s
 => => writing image sha256:5c77c04a1d392f80c2313a5e1acb578e0cdbbbfaede5d83e398f1847620555a6                                                                              0.0s
 => => naming to docker.io/library/sd-lstein:9                                                                                                                            0.0s
[+] Running 1/0
 ⠿ Container webui-docker-lstein-1  Created                                                                                                                               0.0s
Attaching to webui-docker-lstein-1
webui-docker-lstein-1  | Mounted .cache
webui-docker-lstein-1  | Mounted transformers
webui-docker-lstein-1  | Mounted clipseg
webui-docker-lstein-1  | Mounted .cache
webui-docker-lstein-1  | Mounted RealESRGAN
webui-docker-lstein-1  | Mounted transformers
webui-docker-lstein-1  | Mounted GFPGANv1.4.pth
webui-docker-lstein-1  | Mounted Codeformer
webui-docker-lstein-1  | Mounted transformers
webui-docker-lstein-1  | Loading Python libraries...
webui-docker-lstein-1  | 
webui-docker-lstein-1  | Installing bert tokenizer (ignore deprecation errors)...Welcome to InvokeAI. This script will help download the Stable Diffusion weight files
webui-docker-lstein-1  | and other large models that are needed for text to image generation. At any point you may interrupt
webui-docker-lstein-1  | this program and resume later.
webui-docker-lstein-1  | 
webui-docker-lstein-1  | 
webui-docker-lstein-1  | ** DOWNLOADING SUPPORT MODELS **
webui-docker-lstein-1  | 
webui-docker-lstein-1  | 
webui-docker-lstein-1  | A problem occurred during initialization.
webui-docker-lstein-1  | The error was: "[Errno 2] No such file or directory: '/stable-diffusion/models/bert-base-uncased/models--bert-base-uncased'"
webui-docker-lstein-1  | Traceback (most recent call last):
webui-docker-lstein-1  |   File "/stable-diffusion/scripts/configure_invokeai.py", line 746, in main
webui-docker-lstein-1  |     download_bert()
webui-docker-lstein-1  |   File "/stable-diffusion/scripts/configure_invokeai.py", line 419, in download_bert
webui-docker-lstein-1  |     download_from_hf(BertTokenizerFast,'bert-base-uncased')
webui-docker-lstein-1  |   File "/stable-diffusion/scripts/configure_invokeai.py", line 425, in download_from_hf
webui-docker-lstein-1  |     return model_class.from_pretrained(model_name,
webui-docker-lstein-1  |   File "/usr/local/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 1700, in from_pretrained
webui-docker-lstein-1  |     resolved_config_file = cached_file(
webui-docker-lstein-1  |   File "/usr/local/lib/python3.10/site-packages/transformers/utils/hub.py", line 409, in cached_file
webui-docker-lstein-1  |     resolved_file = hf_hub_download(
webui-docker-lstein-1  |   File "/usr/local/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1024, in hf_hub_download
webui-docker-lstein-1  |     os.makedirs(storage_folder, exist_ok=True)
webui-docker-lstein-1  |   File "/usr/local/lib/python3.10/os.py", line 225, in makedirs
webui-docker-lstein-1  |     mkdir(name, mode)
webui-docker-lstein-1  | FileNotFoundError: [Errno 2] No such file or directory: '/stable-diffusion/models/bert-base-uncased/models--bert-base-uncased'
webui-docker-lstein-1  | 
webui-docker-lstein-1  | + python3 -u scripts/invoke.py --web --host 0.0.0.0 --port 7860 --config /docker/models.yaml --root_dir /stable-diffusion --outdir /output
webui-docker-lstein-1  | * Initializing, be patient...
webui-docker-lstein-1  | >> Initialization file /root/.invokeai found. Loading...
webui-docker-lstein-1  | >> InvokeAI runtime directory is "/stable-diffusion"
webui-docker-lstein-1  | >> Patchmatch initialized
webui-docker-lstein-1  | >> GFPGAN Initialized
webui-docker-lstein-1  | ## NOT FOUND: CodeFormer model not found at /stable-diffusion/models/codeformer/codeformer.pth
webui-docker-lstein-1  | >> CodeFormer Disabled
webui-docker-lstein-1  | >> ESRGAN Initialized
webui-docker-lstein-1  | >> Using device_type cuda
webui-docker-lstein-1  | >> Current VRAM usage:  0.00G
webui-docker-lstein-1  | >> Scanning Model: stable-diffusion-1.5
webui-docker-lstein-1  | >> Model Scanned. OK!!
webui-docker-lstein-1  | >> Loading stable-diffusion-1.5 from /data/StableDiffusion/v1-5-pruned-emaonly.ckpt
webui-docker-lstein-1  | >> Calculating sha256 hash of weights file
webui-docker-lstein-1  | >> sha256 = cc6cb27103417325ff94f52b7a5d2dde45a7515b25c255d8e396c90014281516 (7.14s)
webui-docker-lstein-1  |    | LatentDiffusion: Running in eps-prediction mode
webui-docker-lstein-1  |    | DiffusionWrapper has 859.52 M params.
webui-docker-lstein-1  |    | Making attention of type 'vanilla' with 512 in_channels
webui-docker-lstein-1  |    | Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
webui-docker-lstein-1  |    | Making attention of type 'vanilla' with 512 in_channels
webui-docker-lstein-1  | ** model stable-diffusion-1.5 could not be loaded: [Errno 2] No such file or directory: '/stable-diffusion/models/openai/clip-vit-large-patch14/models--openai--clip-vit-large-patch14'
webui-docker-lstein-1  | Traceback (most recent call last):
webui-docker-lstein-1  |   File "/stable-diffusion/ldm/invoke/model_cache.py", line 80, in get_model
webui-docker-lstein-1  |     requested_model, width, height, hash = self._load_model(model_name)
webui-docker-lstein-1  |   File "/stable-diffusion/ldm/invoke/model_cache.py", line 231, in _load_model
webui-docker-lstein-1  |     model = instantiate_from_config(omega_config.model)
webui-docker-lstein-1  |   File "/stable-diffusion/ldm/util.py", line 90, in instantiate_from_config
webui-docker-lstein-1  |     return get_obj_from_str(config['target'])(
webui-docker-lstein-1  |   File "/stable-diffusion/ldm/models/diffusion/ddpm.py", line 658, in __init__
webui-docker-lstein-1  |     self.instantiate_cond_stage(cond_stage_config)
webui-docker-lstein-1  |   File "/stable-diffusion/ldm/models/diffusion/ddpm.py", line 769, in instantiate_cond_stage
webui-docker-lstein-1  |     model = instantiate_from_config(config)
webui-docker-lstein-1  |   File "/stable-diffusion/ldm/util.py", line 90, in instantiate_from_config
webui-docker-lstein-1  |     return get_obj_from_str(config['target'])(
webui-docker-lstein-1  |   File "/stable-diffusion/ldm/modules/encoders/modules.py", line 247, in __init__
webui-docker-lstein-1  |     self.tokenizer = CLIPTokenizer.from_pretrained(
webui-docker-lstein-1  |   File "/usr/local/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 1736, in from_pretrained
webui-docker-lstein-1  |     resolved_vocab_files[file_id] = cached_file(
webui-docker-lstein-1  |   File "/usr/local/lib/python3.10/site-packages/transformers/utils/hub.py", line 409, in cached_file
webui-docker-lstein-1  |     resolved_file = hf_hub_download(
webui-docker-lstein-1  |   File "/usr/local/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1024, in hf_hub_download
webui-docker-lstein-1  |     os.makedirs(storage_folder, exist_ok=True)
webui-docker-lstein-1  |   File "/usr/local/lib/python3.10/os.py", line 225, in makedirs
webui-docker-lstein-1  |     mkdir(name, mode)
webui-docker-lstein-1  | FileNotFoundError: [Errno 2] No such file or directory: '/stable-diffusion/models/openai/clip-vit-large-patch14/models--openai--clip-vit-large-patch14'
webui-docker-lstein-1  | 
webui-docker-lstein-1  | 
webui-docker-lstein-1  | !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
webui-docker-lstein-1  |    You appear to have a missing or misconfigured model file(s).                   
webui-docker-lstein-1  |    The script will now exit and run configure_invokeai.py to help fix the problem.
webui-docker-lstein-1  |    After reconfiguration is done, please relaunch invoke.py.                      
webui-docker-lstein-1  | !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
webui-docker-lstein-1  | configure_invokeai is launching....
webui-docker-lstein-1  | 
webui-docker-lstein-1  | Loading Python libraries...
webui-docker-lstein-1  | 
webui-docker-lstein-1  | Welcome to InvokeAI. This script will help download the Stable Diffusion weight files
webui-docker-lstein-1  | and other large models that are needed for text to image generation. At any point you may interrupt
webui-docker-lstein-1  | this program and resume later.
webui-docker-lstein-1  | 
webui-docker-lstein-1  | ** INITIALIZING INVOKEAI RUNTIME DIRECTORY **
webui-docker-lstein-1  | Select a directory in which to install InvokeAI's models and configuration files [/root/invokeai]: 
webui-docker-lstein-1  | A problem occurred during initialization.
webui-docker-lstein-1  | The error was: "EOF when reading a line"
webui-docker-lstein-1  | Traceback (most recent call last):
webui-docker-lstein-1  |   File "/stable-diffusion/ldm/invoke/model_cache.py", line 80, in get_model
webui-docker-lstein-1  |     requested_model, width, height, hash = self._load_model(model_name)
webui-docker-lstein-1  |   File "/stable-diffusion/ldm/invoke/model_cache.py", line 231, in _load_model
webui-docker-lstein-1  |     model = instantiate_from_config(omega_config.model)
webui-docker-lstein-1  |   File "/stable-diffusion/ldm/util.py", line 90, in instantiate_from_config
webui-docker-lstein-1  |     return get_obj_from_str(config['target'])(
webui-docker-lstein-1  |   File "/stable-diffusion/ldm/models/diffusion/ddpm.py", line 658, in __init__
webui-docker-lstein-1  |     self.instantiate_cond_stage(cond_stage_config)
webui-docker-lstein-1  |   File "/stable-diffusion/ldm/models/diffusion/ddpm.py", line 769, in instantiate_cond_stage
webui-docker-lstein-1  |     model = instantiate_from_config(config)
webui-docker-lstein-1  |   File "/stable-diffusion/ldm/util.py", line 90, in instantiate_from_config
webui-docker-lstein-1  |     return get_obj_from_str(config['target'])(
webui-docker-lstein-1  |   File "/stable-diffusion/ldm/modules/encoders/modules.py", line 247, in __init__
webui-docker-lstein-1  |     self.tokenizer = CLIPTokenizer.from_pretrained(
webui-docker-lstein-1  |   File "/usr/local/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 1736, in from_pretrained
webui-docker-lstein-1  |     resolved_vocab_files[file_id] = cached_file(
webui-docker-lstein-1  |   File "/usr/local/lib/python3.10/site-packages/transformers/utils/hub.py", line 409, in cached_file
webui-docker-lstein-1  |     resolved_file = hf_hub_download(
webui-docker-lstein-1  |   File "/usr/local/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1024, in hf_hub_download
webui-docker-lstein-1  |     os.makedirs(storage_folder, exist_ok=True)
webui-docker-lstein-1  |   File "/usr/local/lib/python3.10/os.py", line 225, in makedirs
webui-docker-lstein-1  |     mkdir(name, mode)
webui-docker-lstein-1  | FileNotFoundError: [Errno 2] No such file or directory: '/stable-diffusion/models/openai/clip-vit-large-patch14/models--openai--clip-vit-large-patch14'
webui-docker-lstein-1  | 
webui-docker-lstein-1  | During handling of the above exception, another exception occurred:
webui-docker-lstein-1  | 
webui-docker-lstein-1  | Traceback (most recent call last):
webui-docker-lstein-1  |   File "/stable-diffusion/ldm/invoke/CLI.py", line 115, in main
webui-docker-lstein-1  |     gen.load_model()
webui-docker-lstein-1  |   File "/stable-diffusion/ldm/generate.py", line 818, in load_model
webui-docker-lstein-1  |     self.set_model(self.model_name)
webui-docker-lstein-1  |   File "/stable-diffusion/ldm/generate.py", line 843, in set_model
webui-docker-lstein-1  |     model_data = cache.get_model(model_name)
webui-docker-lstein-1  |   File "/stable-diffusion/ldm/invoke/model_cache.py", line 91, in get_model
webui-docker-lstein-1  |     assert self.current_model,'** FATAL: no current model to restore to'
webui-docker-lstein-1  | AssertionError: ** FATAL: no current model to restore to
webui-docker-lstein-1  | 
webui-docker-lstein-1  | During handling of the above exception, another exception occurred:
webui-docker-lstein-1  | 
webui-docker-lstein-1  | Traceback (most recent call last):
webui-docker-lstein-1  |   File "/stable-diffusion/scripts/configure_invokeai.py", line 740, in main
webui-docker-lstein-1  |     initialize_rootdir(Globals.root,opt.yes_to_all)
webui-docker-lstein-1  |   File "/stable-diffusion/scripts/configure_invokeai.py", line 608, in initialize_rootdir
webui-docker-lstein-1  |     root = select_root(root,yes_to_all)
webui-docker-lstein-1  |   File "/stable-diffusion/scripts/configure_invokeai.py", line 587, in select_root
webui-docker-lstein-1  |     directory = input(f"Select a directory in which to install InvokeAI's models and configuration files [{default}]: ").strip(' \\')
webui-docker-lstein-1  | EOFError: EOF when reading a line
webui-docker-lstein-1  | 
webui-docker-lstein-1 exited with code 255```
AbdBarho commented 1 year ago

@joshurawr thank you for the detailed report, I managed to reproduce the problem.

AbdBarho commented 1 year ago

@joshurawr could you try again from latest master? if the problem is still there please re-open this issue.

joshurawr commented 1 year ago

fix worked, thank you