Comments (11)
Sorry, Vlad, I feel like I opened the floodgates on you!
LOL. Not blaming you :)
from automatic.
Godspeed, really looking forward to a contender to Auto that doesn't have us waiting forever for important updates.
I've seen a number of exciting things just sitting there and waiting for him to come around and approve. Can't even remember them all anymore, but some optimization stuff, torch 2, an improved sampler or something.
from automatic.
Honestly, after steps 1-3, I used pip install -r requirements.txt pip install -r requirements_versions.txt
and then followed this comment. Now everything is working as it should be.
from automatic.
Ah, that explains why I've been trying for 2 days without stopping to make it work and it wasn't working. Thanks for that information!!
from automatic.
thanks for the work, so what the step if we are windows?
from automatic.
venv "F:\stable-diffusion-webui\venv\Scripts\Python.exe"
Installing requirements for Web UI
Running extension installer: F:\stable-diffusion-webui\extensions\clip-interrogator-ext\install.py
A Installing requirements for CLIP Interrogator
Running extension installer: F:\stable-diffusion-webui\extensions\deforum-for-automatic1111-webui\install.py
Running extension installer: F:\stable-diffusion-webui\extensions\ebsynth_utility\install.py
A current transparent-background 1.2.3
Running extension installer: F:\stable-diffusion-webui\extensions\PBRemTools\install.py
A Installing None
Installing onnxruntime-gpu...
Installing None
Installing opencv-python...
Installing None
Installing Pillow...
Installing None
Installing segmentation-refinement...
Installing None
Installing scikit-learn...
Running extension installer: F:\stable-diffusion-webui\extensions\sd-webui-3d-open-pose-editor\install.py
Running extension installer: F:\stable-diffusion-webui\extensions\sd-webui-controlnet\install.py
Running extension installer: F:\stable-diffusion-webui\extensions\sd-webui-modelscope-text2video\install.py
Running extension installer: F:\stable-diffusion-webui\extensions\sd-webui-nulienhance\install.py
A Installed.
Running extension installer: F:\stable-diffusion-webui\extensions\sd-webui-segment-anything\install.py
Running extension installer: F:\stable-diffusion-webui\extensions\sd_dreambooth_extension\install.py
A Stop Motion CN - Running Preload
Set Gradio Queue: True
If submitting an issue on github, please provide the full startup log for debugging purposes.
Initializing Dreambooth
Dreambooth revision: 926ae204ef5de17efca2059c334b6098492a0641
Successfully installed fastapi-0.94.1 google-auth-oauthlib-0.4.6 tensorboard-2.12.0 transformers-4.26.1
[+] xformers version 0.0.17.dev464 installed.
[+] torch version 2.0.0+cu118 installed.
[+] torchvision version 0.15.1+cu118 installed.
[+] accelerate version 0.18.0 installed.
[+] diffusers version 0.14.0 installed.
[+] transformers version 4.26.1 installed.
[+] bitsandbytes version 0.35.4 installed.
Running extension installer: F:\stable-diffusion-webui\extensions\stable-diffusion-webui-blip2-captioner\install.py
Running extension installer: F:\stable-diffusion-webui\extensions\stable-diffusion-webui-rembg\install.py
Running extension installer: F:\stable-diffusion-webui\extensions\unprompted\install.py
A Installing requirements for Unprompted - img2pez
Installing requirements for Unprompted - pix2pix_zero
Running extension installer: F:\stable-diffusion-webui\extensions\video2video\install.py
A Installing video2video requirement: sk-video
Launching Web UI with arguments: --deepdanbooru --api --no-half-vae --opt-sdp-attention
F:\stable-diffusion-webui\venv\lib\site-packages\pkg_resources_init_.py:123: PkgResourcesDeprecationWarning: otobuf is an invalid version and will not be supported in a future release
warnings.warn(
Stop Motion CN - Running Preload
Set Gradio Queue: True
Error running preload() for F:\stable-diffusion-webui\extensions-builtin\sd-webui-controlnet\preload.py
┌───────────────────────────────────────── Traceback (most recent call last) ─────────────────────────────────────────┐
│ F:\stable-diffusion-webui\modules\script_loading.py:28 in preload_extensions │
│ │
│ 27 if hasattr(module, 'preload'): │
│ > 28 module.preload(parser) │
│ 29 │
│ │
│ F:\stable-diffusion-webui\extensions-builtin\sd-webui-controlnet\preload.py:2 in preload │
│ │
│ 1 def preload(parser): │
│ > 2 parser.add_argument("--controlnet-dir", type=str, help="Path to directory with Contr │
│ 3 parser.add_argument("--no-half-controlnet", action='store_true', help="do not switch │
│ │
│ ... 4 frames hidden ... │
│ │
│ C:\Users\Administrator\AppData\Local\Programs\Python\Python310\lib\argparse.py:1592 in _check_conflict │
│ │
│ 1591 conflict_handler = self._get_handler() │
│ > 1592 conflict_handler(action, confl_optionals) │
│ 1593 │
│ │
│ C:\Users\Administrator\AppData\Local\Programs\Python\Python310\lib\argparse.py:1601 in _handle_conflict_error │
│ │
│ 1600 in conflicting_actions]) │
│ > 1601 raise ArgumentError(action, message % conflict_string) │
│ 1602 │
└─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┘
ArgumentError: argument --controlnet-dir: conflicting option string: --controlnet-dir
During handling of the above exception, another exception occurred:
┌───────────────────────────────────────── Traceback (most recent call last) ─────────────────────────────────────────┐
│ F:\stable-diffusion-webui\launch.py:311 in │
│ │
│ 310 prepare_environment() │
│ > 311 start() │
│ 312 │
│ │
│ F:\stable-diffusion-webui\launch.py:302 in start │
│ │
│ 301 print(f"Launching {'API server' if '--nowebui' in sys.argv else 'Web UI'} with argum │
│ > 302 import webui │
│ 303 if '--nowebui' in sys.argv: │
│ │
│ ... 2 frames hidden ... │
│ │
│ F:\stable-diffusion-webui\modules\shared.py:34 in │
│ │
│ 33 script_loading.preload_extensions(extensions_dir, parser) │
│ > 34 script_loading.preload_extensions(extensions_builtin_dir, parser) │
│ 35 │
│ │
│ F:\stable-diffusion-webui\modules\script_loading.py:32 in preload_extensions │
│ │
│ 31 print(f"Error running preload() for {preload_script}", file=sys.stderr) │
│ > 32 shared.exception() │
│ 33 │
└─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┘
AttributeError: partially initialized module 'modules.shared' has no attribute 'exception' (most likely due to a
circular import)
请按任意键继续. . .
from automatic.
Temp solution:
In Windows is possible to use Git.bash shell (that is installed when you install Git) for run automatic.sh, can be that not run completely but in this way install all submodules then you can do the -m pip install -r requirements.txt pip install -r requirements_versions.txt (if automatic.sh not run completely)
from automatic.
Issue Description
Currently
automatic.sh
installer and launcher script is Linux only. Oldwebui.bat / webui.sh
scripts exist, but they do not have full functionality to install all submodules or even libraries.
Sorry, Vlad, I feel like I opened the floodgates on you!
from automatic.
Major updated posted, see #99 for details
from automatic.
from automatic.
Guys, I appreciate all community troubleshooting efforts!
I've just finished major update to installer/launcher as well as some environment auto-tunes.
Hopefully now those steps should not be needed and should work out-of-the-box
Check README for updated notes
git clone https://github.com/vladmandic/automatic SD
Cloning into 'SD'...
remote: Enumerating objects: 20178, done.
remote: Counting objects: 100% (21/21), done.
remote: Compressing objects: 100% (17/17), done.
remote: Total 20178 (delta 5), reused 6 (delta 4), pack-reused 20157
Receiving objects: 100% (20178/20178), 30.22 MiB | 20.73 MiB/s, done.
Resolving deltas: 100% (14195/14195), done.
webui.bat
venv "D:\SD\venv\Scripts\Python.exe"
Python 3.11.3 on Windows
Running setup
Version: c830bbf7 Thu Apr 13 12:05:42 2023 -0400
Installing requirements
Installing packages
Error running pip with args: install --upgrade --no-deps xformers
Installing repositories
Installing submodules
Updating submodules
Built-in extensions: ['clip-interrogator-ext', 'LDSR', 'Lora', 'prompt-bracket-checker', 'ScuNET', 'sd-dynamic-thresholding', 'sd-extension-aesthetic-scorer', 'sd-extension-steps-animation', 'sd-extension-system-info', 'sd-webui-controlnet', 'sd-webui-model-converter', 'seed_travel', 'stable-diffusion-webui-images-browser', 'stable-diffusion-webui-rembg', 'SwinIR']
Enabled extensions: []
Installing requirements
Setting environment tuning
Torch 2.0.0+cu118
Torch backend: nVidia CUDA 11.8 cuDNN 8700
Torch detected GPU: NVIDIA GeForce RTX 3060 VRAM 12288 Arch (8, 6) Cores 28
Server arguments: []
No module 'xformers'. Proceeding without it.
Downloading: "https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.safetensors" to D:\SD\models\Stable-diffusion\v1-5-pruned-emaonly.safetensors
100% | 3.97G/3.97G [02:47<00:00, 25.5MB/s]
Available models: 1
Image Browser: Creating database
Image Browser: Database created
Running on local URL: http://127.0.0.1:7860
To create a public link, set `share=True` in `launch()`.
Checkpoint model.ckpt not found; loading fallback v1-5-pruned-emaonly.safetensors
Loading weights: D:\SD\models\Stable-diffusion\v1-5-pruned-emaonly.safetensors ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 0.0/4.3 GB -:--:--
Creating model from config: D:\SD\configs\v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Calculating sha256 for D:\SD\models\Stable-diffusion\v1-5-pruned-emaonly.safetensors: 6ce0161689b3853acaa03779ec93eafe75a02f4ced659bee03f50797806fa2fa
Applying scaled dot product cross attention optimization
Textual inversion embeddings loaded(0):
Model loaded in 4.9s (load=0.2s create=0.2s hash=2.8s apply=0.6s vae=0.4s move=0.6s)
Startup time: 186.4s (torch=6.3s libraries=4.2s models=167.3s codeformer=0.2s scripts=1.7s ui=1.4s gradio=0.1s checkpoint=5.2s)
from automatic.
Related Issues (20)
- [Issue]: Python 3.12 unsupported error on initial installation ? HOT 6
- [Issue]: [Issue]: Can't Generate anything (or infinitly slow) HOT 1
- [Issue]: PAG failure while Face Restore enabled HOT 1
- [Issue] Stable Video Diffusion not working
- [Issue]: webui --upgrade turns dev into master HOT 1
- [Issue] Errors with RealESRGAN 4x+ Anime6B on OpenVINO backend HOT 2
- [Feature]: SD Forge Attention Couple better alternative to regional prompter with gui HOT 6
- [Issue]: Modern UI bug - All Icons not showing up HOT 1
- [Issue] Instant ID cuda Cannot copy out of meta tensor HOT 2
- [Feature] sd-forge-layerdiffuse
- [Issue]: dev: "Same as primary" for Secondary Sampler in new UI is not working -> "NullType" error HOT 1
- [Issue]: dev/new ui: sampler options not recognized for UI / Set new defaults, so the toggle states get lost HOT 1
- [Issue]: dev: timestamp AYS SD15 prefills Timesteps override, which must be empty for this selection HOT 2
- [Issue]: dev/new ui: render time and manual save state is missing HOT 4
- [Issue]: Move Face Restore options to Post Process settings HOT 1
- [Issue]: dev/new ui: "Extra networks" columns broken HOT 1
- [Issue]: Wildcard Recursion issues HOT 7
- [Issue]: dev: metadata not saving to png/webp HOT 2
- [Feature]: Wildcards & Batching HOT 2
- [Issue]: ZLUDA installation steps in wiki do not work, caffe2_nvrtc.dll missing HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from automatic.