Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Bug]: Can't create 16 PNG images, and flickers badly!!! #556

Open
2 tasks done
CZ1897 opened this issue Oct 6, 2024 · 1 comment
Open
2 tasks done

[Bug]: Can't create 16 PNG images, and flickers badly!!! #556

CZ1897 opened this issue Oct 6, 2024 · 1 comment

Comments

@CZ1897
Copy link

CZ1897 commented Oct 6, 2024

Is there an existing issue for this?

  • I have searched the existing issues and checked the recent builds/commits of both this extension and the webui

Have you read FAQ on README?

  • I have updated WebUI and this extension to the latest version

What happened?

Can't create 16 PNG images, and flickers badly!!!

The following is my background code👇

My computer configuration
R7 5800X
3060TI 8G
32GB

).ckpt
Applying attention optimization: xformers... done.
QQ20241006-225637

Weights loaded in 13.7s (send model to cpu: 0.5s, calculate hash: 6.4s, load weights from disk: 4.2s, apply weights to model: 1.4s, apply fp8: 0.8s, move model to device: 0.3s).
2024-10-06 22:49:30,391 - AnimateDiff - INFO - AnimateDiff process start.
2024-10-06 22:49:30,391 - AnimateDiff - INFO - Loading motion module mm_sd_v15_v2.ckpt from D:\sd-webui-aki-v4.9\extensions\sd-webui-animatediff\model\mm_sd_v15_v2.ckpt
2024-10-06 22:49:31,550 - AnimateDiff - INFO - Guessed mm_sd_v15_v2.ckpt architecture: MotionModuleType.AnimateDiffV2
2024-10-06 22:49:34,570 - AnimateDiff - INFO - Injecting motion module mm_sd_v15_v2.ckpt into SD1.5 UNet middle block.
2024-10-06 22:49:34,570 - AnimateDiff - INFO - Injecting motion module mm_sd_v15_v2.ckpt into SD1.5 UNet input blocks.
2024-10-06 22:49:34,570 - AnimateDiff - INFO - Injecting motion module mm_sd_v15_v2.ckpt into SD1.5 UNet output blocks.
2024-10-06 22:49:34,570 - AnimateDiff - INFO - Setting DDIM alpha.
2024-10-06 22:49:34,586 - AnimateDiff - INFO - Injection finished.
2024-10-06 22:49:34,586 - AnimateDiff - INFO - AnimateDiff + ControlNet will generate 16 frames.
2024-10-06 22:49:36,007 - AnimateDiff - INFO - Randomizing init_latent according to [1.0, 0.96875, 0.9375, 0.90625, 0.875, 0.84375, 0.8125, 0.78125, 0.75, 0.71875, 0.6875, 0.65625, 0.625, 0.59375, 0.5625, 0.53125].
2024-10-06 22:49:36,530 - AnimateDiff - INFO - inner model forward hooked
2024-10-06 22:49:40,648 - AnimateDiff - INFO - Restoring DDIM alpha.
2024-10-06 22:49:40,649 - AnimateDiff - INFO - Removing motion module from SD1.5 UNet input blocks.
2024-10-06 22:49:40,649 - AnimateDiff - INFO - Removing motion module from SD1.5 UNet output blocks.
2024-10-06 22:49:40,649 - AnimateDiff - INFO - Removing motion module from SD1.5 UNet middle block.
2024-10-06 22:49:40,649 - AnimateDiff - INFO - Removal finished.
2024-10-06 22:49:40,650 - AnimateDiff - INFO - Saving output formats: GIF

00012-3734559667
QQ20241006-225630

Steps to reproduce the problem

  1. Go to ....
  2. Press ....
  3. ...

What should have happened?

Generate 16 PNG animations normally

Commit where the problem happens

webui: SD
extension:

What browsers do you use to access the UI ?

Microsoft Edge

Command Line Arguments

NO

Console logs

nsors
Creating model from config: D:\sd-webui-aki-v4.9\configs\v1-inference.yaml
Applying attention optimization: xformers... done.
Model loaded in 3.7s (create model: 0.3s, apply weights to model: 3.2s).
2024-10-06 22:56:09,482 - AnimateDiff - INFO - AnimateDiff process start.
2024-10-06 22:56:09,526 - AnimateDiff - INFO - Injecting motion module mm_sd_v15_v2.ckpt into SD1.5 UNet middle block.
2024-10-06 22:56:09,527 - AnimateDiff - INFO - Injecting motion module mm_sd_v15_v2.ckpt into SD1.5 UNet input blocks.
2024-10-06 22:56:09,527 - AnimateDiff - INFO - Injecting motion module mm_sd_v15_v2.ckpt into SD1.5 UNet output blocks.
2024-10-06 22:56:09,527 - AnimateDiff - INFO - Setting DDIM alpha.
2024-10-06 22:56:09,529 - AnimateDiff - INFO - Injection finished.
2024-10-06 22:56:09,529 - AnimateDiff - INFO - AnimateDiff + ControlNet will generate 16 frames.
2024-10-06 22:56:10,802 - AnimateDiff - INFO - Randomizing init_latent according to [1.0, 0.96875, 0.9375, 0.90625, 0.875, 0.84375, 0.8125, 0.78125, 0.75, 0.71875, 0.6875, 0.65625, 0.625, 0.59375, 0.5625, 0.53125].
2024-10-06 22:56:11,248 - AnimateDiff - INFO - inner model forward hooked
2024-10-06 22:56:18,080 - AnimateDiff - INFO - Restoring DDIM alpha.
2024-10-06 22:56:18,080 - AnimateDiff - INFO - Removing motion module from SD1.5 UNet input blocks.
2024-10-06 22:56:18,080 - AnimateDiff - INFO - Removing motion module from SD1.5 UNet output blocks.
2024-10-06 22:56:18,080 - AnimateDiff - INFO - Removing motion module from SD1.5 UNet middle block.
2024-10-06 22:56:18,080 - AnimateDiff - INFO - Removal finished.
2024-10-06 22:56:18,081 - AnimateDiff - INFO - Saving output formats: GIF

Additional information

No response

@zappityzap
Copy link
Collaborator

img2img with an init image doesn't work that well in AnimateDiff. Stable Video Diffusion or CogVideo are better for this.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants