search

kabachuha / sd-webui-text2video

Auto1111 extension implementing text2video diffusion models (like ModelScope or VideoCrafter) using only Auto1111 webui dependencies
Other
1.28k stars 106 forks source link

[Bug]: Exception occurred: can't delete attribute 'sd_model' #155

Closed sanatorios closed 1 year ago

sanatorios commented 1 year ago

Is there an existing issue for this?

Are you using the latest version of the extension?

What happened?

Today I tried to set up the text2video model but it's having this bug in the cmd: AttributeError: can't delete attribute 'sd_model' Exception occurred: can't delete attribute 'sd_model'. __ Already up to date. venv "C:\Users\Dario\Desktop\WEBUI_STABLEDFFF\AI\stable-diffusion-webui\venv\Scripts\Python.exe" Python 3.10.8 (tags/v3.10.8:aaaf517, Oct 11 2022, 16:50:30) [MSC v.1933 64 bit (AMD64)] Version: v1.2.1 Commit hash: 89f9faa63388756314e8a1d96cf86bf5e0663045 Installing requirements

Installing requirements 1 for Infinite-Zoom

Installing imageio-ffmpeg requirement for depthmap script Installing pyqt5 requirement for depthmap script

Launching Web UI with arguments: --xformers [AddNet] Updating model hashes... 100%|███████████████████████████████████████████████████████████████████████████████| 12/12 [00:00<00:00, 12035.31it/s] [AddNet] Updating model hashes... 100%|███████████████████████████████████████████████████████████████████████████████| 12/12 [00:00<00:00, 12041.06it/s] ControlNet v1.1.166 ControlNet v1.1.166 Loading weights [e1441589a6] from C:\Users\Dario\Desktop\WEBUI_STABLEDFFF\AI\stable-diffusion-webui\models\Stable-diffusion\v1-5-pruned.ckpt Deforum ControlNet support: enabled Running on local URL: http://127.0.0.1:7860

To create a public link, set share=True in launch(). Startup time: 14.6s (import torch: 3.9s, import gradio: 1.2s, import ldm: 0.5s, other imports: 1.0s, load scripts: 4.4s, create ui: 3.4s, gradio launch: 0.1s). Creating model from config: C:\Users\Dario\Desktop\WEBUI_STABLEDFFF\AI\stable-diffusion-webui\configs\v1-inference.yaml LatentDiffusion: Running in eps-prediction mode DiffusionWrapper has 859.52 M params. Applying xformers cross attention optimization. Textual inversion embeddings loaded(0): Textual inversion embeddings skipped(1): glitch Model loaded in 7.2s (load weights from disk: 3.8s, create model: 0.4s, apply weights to model: 0.5s, apply half(): 0.6s, move model to device: 0.9s, load textual inversion embeddings: 1.0s). text2video — The model selected is: ModelScope text2video extension for auto1111 webui Git commit: 26822483 (Thu May 4 18:26:12 2023) Traceback (most recent call last): File "C:\Users\Dario\Desktop\WEBUI_STABLEDFFF\AI\stable-diffusion-webui/extensions/sd-webui-text2video/scripts\t2v_helpers\render.py", line 24, in run vids_pack = process_modelscope(args_dict) File "C:\Users\Dario\Desktop\WEBUI_STABLEDFFF\AI\stable-diffusion-webui/extensions/sd-webui-text2video/scripts\modelscope\process_modelscope.py", line 45, in process_modelscope del shared.sd_model AttributeError: can't delete attribute 'sd_model' Exception occurred: can't delete attribute 'sd_model' text2video — The model selected is: ModelScope text2video extension for auto1111 webui Git commit: 26822483 (Thu May 4 18:26:12 2023) Traceback (most recent call last): File "C:\Users\Dario\Desktop\WEBUI_STABLEDFFF\AI\stable-diffusion-webui/extensions/sd-webui-text2video/scripts\t2v_helpers\render.py", line 24, in run vids_pack = process_modelscope(args_dict) File "C:\Users\Dario\Desktop\WEBUI_STABLEDFFF\AI\stable-diffusion-webui/extensions/sd-webui-text2video/scripts\modelscope\process_modelscope.py", line 45, in process_modelscope del shared.sd_model AttributeError: can't delete attribute 'sd_model' Exception occurred: can't delete attribute 'sd_model'

Steps to reproduce the problem

1.Go to Automatic webui1111

  1. Press Generate on text2video extension ...

What should have happened?

It shoud generate a video. No issues encountered previously as today.

WebUI and Deforum extension Commit IDs

webui commit id - 89f9faa63388756314e8a1d96cf86bf5e0663045 txt2vid commit id - 26822483

Torch version

v1.2.1

What GPU were you using for launching?

2080TI

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

Local PC setup (Windows)

Settings

Image 2247

Console logs

Already up to date.
venv "C:\Users\Dario\Desktop\WEBUI_STABLEDFFF\AI\stable-diffusion-webui\venv\Scripts\Python.exe"
Python 3.10.8 (tags/v3.10.8:aaaf517, Oct 11 2022, 16:50:30) [MSC v.1933 64 bit (AMD64)]
Version: v1.2.1
Commit hash: 89f9faa63388756314e8a1d96cf86bf5e0663045
Installing requirements

Installing requirements 1 for Infinite-Zoom

Installing imageio-ffmpeg requirement for depthmap script
Installing pyqt5 requirement for depthmap script

Launching Web UI with arguments: --xformers
[AddNet] Updating model hashes...
100%|███████████████████████████████████████████████████████████████████████████████| 12/12 [00:00<00:00, 12035.31it/s]
[AddNet] Updating model hashes...
100%|███████████████████████████████████████████████████████████████████████████████| 12/12 [00:00<00:00, 12041.06it/s]
ControlNet v1.1.166
ControlNet v1.1.166
Loading weights [e1441589a6] from C:\Users\Dario\Desktop\WEBUI_STABLEDFFF\AI\stable-diffusion-webui\models\Stable-diffusion\v1-5-pruned.ckpt
*Deforum ControlNet support: enabled*
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Startup time: 14.6s (import torch: 3.9s, import gradio: 1.2s, import ldm: 0.5s, other imports: 1.0s, load scripts: 4.4s, create ui: 3.4s, gradio launch: 0.1s).
Creating model from config: C:\Users\Dario\Desktop\WEBUI_STABLEDFFF\AI\stable-diffusion-webui\configs\v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Applying xformers cross attention optimization.
Textual inversion embeddings loaded(0):
Textual inversion embeddings skipped(1): glitch
Model loaded in 7.2s (load weights from disk: 3.8s, create model: 0.4s, apply weights to model: 0.5s, apply half(): 0.6s, move model to device: 0.9s, load textual inversion embeddings: 1.0s).
text2video — The model selected is:  ModelScope
 text2video extension for auto1111 webui
Git commit: 26822483 (Thu May  4 18:26:12 2023)
Traceback (most recent call last):
  File "C:\Users\Dario\Desktop\WEBUI_STABLEDFFF\AI\stable-diffusion-webui/extensions/sd-webui-text2video/scripts\t2v_helpers\render.py", line 24, in run
    vids_pack = process_modelscope(args_dict)
  File "C:\Users\Dario\Desktop\WEBUI_STABLEDFFF\AI\stable-diffusion-webui/extensions/sd-webui-text2video/scripts\modelscope\process_modelscope.py", line 45, in process_modelscope
    del shared.sd_model
AttributeError: can't delete attribute 'sd_model'
Exception occurred: can't delete attribute 'sd_model'
text2video — The model selected is:  ModelScope
 text2video extension for auto1111 webui
Git commit: 26822483 (Thu May  4 18:26:12 2023)
Traceback (most recent call last):
  File "C:\Users\Dario\Desktop\WEBUI_STABLEDFFF\AI\stable-diffusion-webui/extensions/sd-webui-text2video/scripts\t2v_helpers\render.py", line 24, in run
    vids_pack = process_modelscope(args_dict)
  File "C:\Users\Dario\Desktop\WEBUI_STABLEDFFF\AI\stable-diffusion-webui/extensions/sd-webui-text2video/scripts\modelscope\process_modelscope.py", line 45, in process_modelscope
    del shared.sd_model
AttributeError: can't delete attribute 'sd_model'
Exception occurred: can't delete attribute 'sd_model'

Additional information

Using animov models by Strangeman3107 and Kabachuha setup.

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: