[Bug]: AnimateDiff - WARNING - No motion module detected

ununiform commented 4 months ago

Is there an existing issue for this?

[X] 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?

[X] I have updated WebUI and this extension to the latest version

What happened?

I have the models installed in /Users/[ME]/stable-diffusion-webui/extensions/sd-webui-animatediff/model But I'm getting the error:

AnimateDiff - WARNING - No motion module detected, falling back to the original forward. You are most likely using !Adetailer. !Adetailer post-process your outputs sequentially, and there will NOT be motion module in your UNet, so there might be NO temporal consistency within the inpainted face. Use at your own risk. If you really want to pursue inpainting with AnimateDiff inserted into UNet, use Segment Anything to generate masks for each frame and inpaint them with AnimateDiff + ControlNet. Note that my proposal might be good or bad, do your own research to figure out the best way.

I'm not using ADetailer

Steps to reproduce the problem

I've installed the models and try to generate a 4 frame animation. No luck. Error appears upon clicking Generate

What should have happened?

I was expecting it to render 4 frames using Animatediff. This is my first time so I'm not sure what to expect.

Commit where the problem happens

webui: automatic1111 extension: AnimateDiff

What browsers do you use to access the UI ?

No response

Command Line Arguments

No

Console logs

None. No errors in console

Additional information

No response

zappityzap commented 4 months ago

Please share the entire output of the console.

Smith15hypeh commented 3 months ago

2024-05-06 21:56:11,852 - AnimateDiff - WARNING - No motion module detected, falling back to the original forward. You are most likely using !Adetailer. !Adetailer post-process your outputs sequentially, and there will NOT be motion module in your UNet, so there might be NO temporal consistency within the inpainted face. Use at your own risk. If you really want to pursue inpainting with AnimateDiff inserted into UNet, use Segment Anything to generate masks for each frame and inpaint them with AnimateDiff + ControlNet. Note that my proposal might be good or bad, do your own research to figure out the best way.

0: 640x640 1 hand, 14.0ms Speed: 4.0ms preprocess, 14.0ms inference, 3.0ms postprocess per image at shape (1, 3, 640, 640) 2024-05-06 21:56:16,786 - AnimateDiff - WARNING - No motion module detected, falling back to the original forward. You are most likely using !Adetailer. !Adetailer post-process your outputs sequentially, and there will NOT be motion module in your UNet, so there might be NO temporal consistency within the inpainted face. Use at your own risk. If you really want to pursue inpainting with AnimateDiff inserted into UNet, use Segment Anything to generate masks for each frame and inpaint them with AnimateDiff + ControlNet. Note that my proposal might be good or bad, do your own research to figure out the best way. 2024-05-06 21:56:20,469 - AnimateDiff - INFO - AnimateDiff process start. 2024-05-06 21:56:20,482 - AnimateDiff - INFO - Injecting motion module mm_sd15_v3.safetensors into SD1.5 UNet input blocks. 2024-05-06 21:56:20,482 - AnimateDiff - INFO - Injecting motion module mm_sd15_v3.safetensors into SD1.5 UNet output blocks. 2024-05-06 21:56:20,483 - AnimateDiff - INFO - Setting DDIM alpha. 2024-05-06 21:56:20,487 - AnimateDiff - INFO - Injection finished. 2024-05-06 21:56:20,487 - AnimateDiff - INFO - AnimateDiff + ControlNet will generate 16 frames AnimateDiff - WARNING - prompt is not str, cannot support prompt map

I have installed two required motion module. Whether I use the !Adetailer or not,the error still exists. I don't know why.

ununiform commented 3 months ago

I'm experiencing the same issue. The motion modules are in the correct folder. I'm not using ADetailer.

If you find a solution, please share.

zappityzap commented 3 months ago

I saw this error come up when attempting to use an SDXL checkpoint with a non-SDXL motion module. The actual error was in the console log above the errors that have been shared here.

ununiform commented 3 months ago

Loading weights [cc6cb27103] from /Users/jaygarett/stable-diffusion-webui/models/Stable-diffusion/v1-5-pruned-emaonly.ckpt Applying attention optimization: sub-quadratic... done. Weights loaded in 2.7s (send model to cpu: 0.6s, load weights from disk: 0.9s, apply weights to model: 0.5s, move model to device: 0.7s). 2024-05-26 17:54:39,448 - AnimateDiff - INFO - AnimateDiff process start. ** Error running before_process: /Users/jaygarett/stable-diffusion-webui/extensions/sd-webui-animatediff/scripts/animatediff.py Traceback (most recent call last): File "/Users/jaygarett/stable-diffusion-webui/modules/scripts.py", line 817, in before_process script.before_process(p, script_args) File "/Users/jaygarett/stable-diffusion-webui/extensions/sd-webui-animatediff/scripts/animatediff.py", line 64, in before_process motion_module.inject(p.sd_model, params.model) File "/Users/jaygarett/stable-diffusion-webui/extensions/sd-webui-animatediff/scripts/animatediff_mm.py", line 76, in inject elif self.mm.enable_gn_hack(): File "/Users/jaygarett/stable-diffusion-webui/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1614, in getattr raise AttributeError("'{}' object has no attribute '{}'".format( AttributeError: 'MotionWrapper' object has no attribute 'enable_gn_hack'

0%| | 0/30 [00:00<?, ?it/s]2024-05-26 17:54:39,961 - AnimateDiff - WARNING - No motion module detected, falling back to the original forward. You are most likely using !Adetailer. !Adetailer post-process your outputs sequentially, and there will NOT be motion module in your UNet, so there might be NO temporal consistency within the inpainted face. Use at your own risk. If you really want to pursue inpainting with AnimateDiff inserted into UNet, use Segment Anything to generate masks for each frame and inpaint them with AnimateDiff + ControlNet. Note that my proposal might be good or bad, do your own research to figure out the best way.

*****!!!!!!! I'm not using ADetailer

ghost commented 2 months ago

Getting the same error after a restart, Everything worked prior to the restart of the computer, same error message:

AnimateDiff - WARNING - No motion module detected, falling back to the original forward. You are most likely using !Adetailer. !Adetailer post-process your outputs sequentially, and there will NOT be motion module in your UNet, so there might be NO temporal consistency within the inpainted face. Use at your own risk. If you really want to pursue inpainting with AnimateDiff inserted into UNet, use Segment Anything to generate masks for each frame and inpaint them with AnimateDiff + ControlNet. Note that my proposal might be good or bad, do your own research to figure out the best way.

zappityzap commented 2 months ago

Can't troubleshoot without details. Need the full console log from the moment the application is launched, versions of software, generation settings, and any other steps needed to reproduce the error.

continue-revolution / sd-webui-animatediff