kabachuha / sd-webui-text2video

Auto1111 extension implementing text2video diffusion models (like ModelScope or VideoCrafter) using only Auto1111 webui dependencies
Other
1.29k stars 108 forks source link

[Bug]: On vladomatic-Automatic:'Namespace' object has no attribute 'force_enable_xformers #181

Closed ShmuelRonen closed 1 year ago

ShmuelRonen commented 1 year ago

Is there an existing issue for this?

Are you using the latest version of the extension?

What happened?

When running the text2video extension on Vladomatic-Automatic, the following error is received during startup:

File "D:\Path\SD\automatic\extensions\sd-webui-text2video\scripts\modelscope\t2v_model.py", line 492, in forward if cmd_opts.force_enable_xformers or (cmd_opts.xformers and shared.xformers_available and torch.version.cuda and (6, 0) <= torch.cuda.get_device_capability(shared.device) <= (9, 0)): AttributeError: 'Namespace' object has no attribute 'force_enable_xformers' Exception occurred: 'Namespace' object has no attribute 'force_enable_xformers'

I discussed this with the developer and he wrote me the following:

it's because extension checks cmdflags which are different. Extension should check if xformers are enabled or not, not check cmdflags from core app ever.

I cannot support extensions that do things the wrong way and hard code things that prevent any kind of change ever.

What fails is extension check of core repo command line flags - which it should never do. And that fails because flags are clearly different.

Steps to reproduce the problem

  1. Write a prompt
  2. Press on execute
  3. The error come...

What should have happened?

A video

WebUI and Deforum extension Commit IDs

webui commit id - txt2vid commit id -

Torch version

23:47:45-511774 INFO Starting SD.Next 23:47:45-516774 INFO Python 3.10.7 on Windows 23:47:45-619776 INFO Version: 4867dafa Fri Jun 23 08:00:51 2023 -0400 23:47:46-226790 INFO nVidia CUDA toolkit detected 23:47:47-757776 INFO Torch 2.0.1+cu118 23:47:47-774774 INFO Torch backend: nVidia CUDA 11.8 cuDNN 8700 23:47:47-778774 INFO Torch detected GPU: NVIDIA GeForce RTX 3090 VRAM 24576 Arch (8, 6) Cores 82

What GPU were you using for launching?

nVidia CUDA 11.8 cuDNN 8700

On which platform are you launching the webui backend with the extension?

Local PC setup (Windows)

Settings

Windows 10 Pro

Console logs

Using VENV: C:\vlad\automatic\venv 23:47:45-511774 INFO Starting SD.Next 23:47:45-516774 INFO Python 3.10.7 on Windows 23:47:45-619776 INFO Version: 4867dafa Fri Jun 23 08:00:51 2023 -0400 23:47:46-226790 INFO nVidia CUDA toolkit detected 23:47:47-757776 INFO Torch 2.0.1+cu118 23:47:47-774774 INFO Torch backend: nVidia CUDA 11.8 cuDNN 8700 23:47:47-778774 INFO Torch detected GPU: NVIDIA GeForce RTX 3090 VRAM 24576 Arch (8, 6) Cores 82 23:47:47-965774 WARNING Modified files: ['modules/lora'] 23:47:48-055775 INFO Disabled extensions-builtin: ['sd-webui-agent-scheduler'] 23:47:48-058777 INFO Enabled extensions-builtin: ['a1111-sd-webui-lycoris', 'clip-interrogator-ext', 'LDSR', 'Lora', 'multidiffusion-upscaler-for-automatic1111', 'ScuNET', 'sd-dynamic-thresholding', 'sd-extension-aesthetic-scorer', 'sd-extension-system-info', 'sd-webui-controlnet', 'seed_travel', 'stable-diffusion-webui-images-browser', 'stable-diffusion-webui-rembg', 'SwinIR'] 23:47:48-071774 INFO Disabled extensions: ['sd-webui-agent-scheduler'] 23:47:48-073774 INFO Enabled extensions: ['animator_extension', 'Auto-Photoshop-StableDiffusion-Plugin', 'canvas-zoom', 'checkpoints', 'deforum-for-automatic1111-webui', 'infinite-zoom-automatic1111-webui', 'SD-CN-Animation', 'sd-webui-aspect-ratio-helper', 'sd-webui-inpaint-anything', 'sd-webui-segment-anything', 'sd-webui-stablesr', 'TemporalKit', 'ultimate-upscale-for-automatic1111', 'unprompted'] 23:47:48-090775 INFO Verifying requirements 23:47:48-103774 INFO Verifying packages 23:47:48-105775 INFO Installing repositories 23:47:52-725776 INFO Installing submodules 23:47:55-278775 INFO Updating submodules 23:48:35-230808 ERROR Error running extension installer: C:\vlad\automatic\extensions\animator_extension\install.py 23:49:07-307845 INFO Extensions enabled: ['a1111-sd-webui-lycoris', 'clip-interrogator-ext', 'LDSR', 'Lora', 'multidiffusion-upscaler-for-automatic1111', 'ScuNET', 'sd-dynamic-thresholding', 'sd-extension-aesthetic-scorer', 'sd-extension-system-info', 'sd-webui-controlnet', 'seed_travel', 'stable-diffusion-webui-images-browser', 'stable-diffusion-webui-rembg', 'SwinIR', 'animator_extension', 'Auto-Photoshop-StableDiffusion-Plugin', 'canvas-zoom', 'checkpoints', 'deforum-for-automatic1111-webui', 'infinite-zoom-automatic1111-webui', 'SD-CN-Animation', 'sd-webui-aspect-ratio-helper', 'sd-webui-inpaint-anything', 'sd-webui-segment-anything', 'sd-webui-stablesr', 'TemporalKit', 'ultimate-upscale-for-automatic1111', 'unprompted'] 23:49:07-318846 INFO Updating Wiki 23:49:08-242847 WARNING Setup complete with errors: 1 23:49:08-245848 WARNING See log file for more details: C:\vlad\automatic\sdnext.log 23:49:08-250846 INFO Extension preload: 0.0s C:\vlad\automatic\extensions-builtin 23:49:08-253847 INFO Extension preload: 0.0s C:\vlad\automatic\extensions 23:49:08-273848 INFO Server arguments: [] No module 'xformers'. Proceeding without it. 23:49:15-096845 INFO Libraries loaded 23:49:15-101846 INFO Using data path: C:\vlad\automatic 23:49:15-106845 INFO Available VAEs: C:\vlad\automatic\models\VAE 2 23:49:15-117845 INFO Available models: C:\vlad\automatic\models\Stable-diffusion 23 23:49:17-703845 INFO ControlNet v1.1.227 ControlNet v1.1.227 ControlNet preprocessor location: C:\vlad\automatic\extensions-builtin\sd-webui-controlnet\annotator\downloads 23:49:17-907847 INFO ControlNet v1.1.227 ControlNet v1.1.227 python_server_full_path: C:\vlad\automatic\extensions\Auto-Photoshop-StableDiffusion-Plugin\server/python_server 23:49:19-053848 INFO Libraries loaded Libraries loaded Loading weights: C:\vlad\automatic\models\Stable-diffusion\revAnimated_v122.safetensors ------------ 0.0/4.2 GB -:--:-- 23:49:19-668847 INFO Setting Torch parameters: dtype=torch.float16 vae=torch.float16 unet=torch.float16 Setting Torch parameters: dtype=torch.float16 vae=torch.float16 unet=torch.float16 LatentDiffusion: Running in eps-prediction mode DiffusionWrapper has 859.52 M params. Loading weights: C:\vlad\automatic\models\VAE\vae-ft-mse-840000-ema-pruned.safetensors ------------ 0.0/334.6 -:--:-- MB 23:49:22-736847 INFO Applying scaled dot product cross attention optimization Applying scaled dot product cross attention optimization 23:49:22-768847 INFO Embeddings: loaded=0 skipped=0 Embeddings: loaded=0 skipped=0 23:49:22-776847 INFO Model loaded in 3.3s (load=0.2s create=0.4s apply=0.6s vae=0.8s move=1.3s) Model loaded in 3.3s (load=0.2s create=0.4s apply=0.6s vae=0.8s move=1.3s) 23:49:23-047846 INFO Model load finished: {'ram': {'used': 5.18, 'total': 31.24}, 'gpu': {'used': 3.3, 'total': 24.0}, 'retries': 0, 'oom': 0} cached=0 Model load finished: {'ram': {'used': 5.18, 'total': 31.24}, 'gpu': {'used': 3.3, 'total': 24.0}, 'retries': 0, 'oom': 0} cached=0 (SETUP) Loading Unprompted v9.2.0 by Therefore Games (SETUP) Initializing Unprompted object... (SETUP) Loading configuration files... (SETUP) Logging enabled for the following message types: RESULT,ERROR 23:49:27-282845 INFO Loading UI theme: name=gradio/default style=Auto Deforum ControlNet support: enabled Running on local URL: http://127.0.0.1:7860 23:49:34-122846 INFO Local URL: http://127.0.0.1:7860/ 23:49:34-124847 INFO Initializing middleware 23:49:35-089846 INFO Startup time: 26.8s (torch=3.6s gradio=1.1s libraries=2.1s codeformer=0.1s scripts=11.8s onchange=0.3s ui=5.9s launch=0.9s app-started=0.1s checkpoint=0.9s)



### Additional information

_No response_
github-actions[bot] commented 1 year ago

This issue has been closed due to incorrect formatting. Please address the following mistakes and reopen the issue:

ShmuelRonen commented 1 year ago

This issue has been closed due to incorrect formatting. Please address the following mistakes and reopen the issue:

  • Include THE FULL LOG FROM THE START OF THE WEBUI in the issue description.

I do