NUROISEA/anime-webui-colab

No reason crash on starting

Closed this issue Β· 0 comments

Archinect commented

Log

πŸ‘ Utility script imported.
🌟 Installing stable-diffusion-webui...
πŸ“¦ Installing 12 extensions...
  β”” aspect-ratio-preset
  β”” batchlinks
  β”” cutoff
  β”” dynamic-thresholding
  β”” images-browser
  β”” latent-couple-two-shot
  β”” session-organizer
  β”” state
  β”” tagcomplete
  β”” tiled-multidiffusion-upscaler
  β”” tokenizer
  β”” tunnels
πŸ”§ Fetching configs...
πŸ’‰ Fetching embeddings...
🩹 Applying web UI Colab patches...
🩹 Applying Colab memory patches...
env: LD_PRELOAD=/content/libtcmalloc_minimal.so.4
πŸ“¦ Installing aria2...
⏬ Downloading anything-v4.0-pruned.safetensors to /content/stable-diffusion-webui/models/Stable-diffusion...
⏬ Downloading anything-v4.0.vae.pt to /content/stable-diffusion-webui/models/VAE...
/content/stable-diffusion-webui
fatal: No names found, cannot describe anything.
Python 3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]
Version: ## 1.4.0
Commit hash: 394ffa7b0a7fff3ec484bcd084e673a8b301ccc8
Installing gfpgan
Installing clip
Installing open_clip
Cloning Stable Diffusion into /content/stable-diffusion-webui/repositories/stable-diffusion-stability-ai...
Cloning K-diffusion into /content/stable-diffusion-webui/repositories/k-diffusion...
Cloning CodeFormer into /content/stable-diffusion-webui/repositories/CodeFormer...
Cloning BLIP into /content/stable-diffusion-webui/repositories/BLIP...
Installing requirements for CodeFormer
Installing requirements
Installing ImageReward requirement for image browser


Installing pycloudflared

Launching Web UI with arguments: --opt-sdp-attention --lowram --no-hashing --enable-insecure-extension-access --no-half-vae --disable-safe-unpickle --gradio-queue --ckpt /content/stable-diffusion-webui/models/Stable-diffusion/anything-v4.0-pruned.safetensors --vae-path /content/stable-diffusion-webui/models/VAE/anything-v4.0.vae.pt --share
No module 'xformers'. Proceeding without it.
Image Browser: ImageReward is not installed, cannot be used.
Image Browser: Creating database
Image Browser: Database created
Loading weights [None] from /content/stable-diffusion-webui/models/Stable-diffusion/anything-v4.0-pruned.safetensors
Running on local URL:  http://127.0.0.1:7860/
preload_extensions_git_metadata for 19 extensions took 0.71s
Running on public URL: https://cf382503c7db26d2d6.gradio.live/

This share link expires in 72 hours. For free permanent hosting and GPU upgrades (NEW!), check out Spaces: https://huggingface.co/spaces
Startup time: 23.3s (import torch: 6.8s, import gradio: 0.9s, import ldm: 0.5s, other imports: 1.8s, setup codeformer: 0.2s, load scripts: 1.9s, create ui: 1.5s, gradio launch: 9.6s).
Creating model from config: /content/stable-diffusion-webui/configs/v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Downloading (…)olve/main/vocab.json: 100% 961k/961k [00:00<00:00, 6.00MB/s]
Downloading (…)olve/main/merges.txt: 100% 525k/525k [00:00<00:00, 6.25MB/s]
Downloading (…)cial_tokens_map.json: 100% 389/389 [00:00<00:00, 1.72MB/s]
Downloading (…)okenizer_config.json: 100% 905/905 [00:00<00:00, 4.29MB/s]
Downloading (…)lve/main/config.json: 100% 4.52k/4.52k [00:00<00:00, 16.8MB/s]
Loading VAE weights from commandline argument: /content/stable-diffusion-webui/models/VAE/anything-v4.0.vae.pt
Applying attention optimization: sdp... done.
Textual inversion embeddings loaded(7): bad-artist, bad-artist-anime, bad-hands-5, bad-image-v2-39000, bad_prompt_version2, EasyNegative, EasyNegativeV2
Model loaded in 49.8s (load weights from disk: 33.8s, create model: 2.0s, apply weights to model: 3.2s, apply half(): 3.4s, load VAE: 4.9s, move model to device: 2.3s, calculate empty prompt: 0.2s).

Settings

[ ]
Select a model before running

⭐ Model selection [[?]](https://github.com/NUROISEA/anime-webui-colab/wiki/Selecting-a-model)
It could take 4-7 minutes to see a link to the web UI, please be patient! :)

model:

anything-v4.0-pruned.safetensors
Select ControlNet models to use [[?]](https://github.com/NUROISEA/anime-webui-colab/wiki/Selecting-ControlNet-models)

controlnet:

none
πŸ”§ Web UI settings
This option only affects the first launch [[?]](https://github.com/NUROISEA/anime-webui-colab/wiki/First-launch-web-UI-settings)

webui_version:

stable
extensions_version:

stable
This saves your generation to Google Drive [[?]](https://github.com/NUROISEA/anime-webui-colab/wiki/Saving-outputs-to-Google-Drive)

outputs_to_drive:

output_drive_folder:
AI/Generated
Change tunnels if you have connection issues with gradio [[?]](https://github.com/NUROISEA/anime-webui-colab/wiki/Using-different-tunnels)

tunnel:

gradio
ngrok_token:
Π’ΡΡ‚Π°Π²ΡŒΡ‚Π΅ Π·Π½Π°Ρ‡Π΅Π½ΠΈΠ΅ (text)
ngrok_region:

auto
Did something break? Please report it on [Github](https://github.com/NUROISEA/anime-webui-colab/issues) or fill out this [Google Form](https://colab.research.google.com/corgiredirector?site=https%3A%2F%2Fforms.gle%2FdnaJojPR4yqvr9dN8) (no sign-in needed)!

After a starting a model, it works 5-10 mins and stopped without error.
link:
https://colab.research.google.com/github/NUROISEA/anime-webui-colab/blob/main/notebooks/anything_v4.ipynb