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

ComfyUI Support In Progress #5

Open
Kosinkadink opened this issue Aug 19, 2024 · 4 comments
Open

ComfyUI Support In Progress #5

Kosinkadink opened this issue Aug 19, 2024 · 4 comments

Comments

@Kosinkadink
Copy link

Hey,

I'll have support added for FancyVideo in AnimateDiff-Evolved nodepack within the next day or two. Thanks for releasing the code and model so soon!

I'll update this issue once the port is complete.

@puffy310
Copy link

I'm very excited!

@gt732
Copy link

gt732 commented Aug 24, 2024

Subscribed!

@zeusftk
Copy link

zeusftk commented Aug 25, 2024

I can't wait anymore

@Kosinkadink
Copy link
Author

I have a question for the developers/paper authors: is it intentional that this repo and the provided models don't actually use or have any of the Cross-frame Textual Guidance? The value for cross_frame_txtattn is False for all demo configs, and the relevant keys to fill out ctm_b_self_module and ctm_b_cross_module are not present. I almost have the ComfyUI implementation finished, but it seems very odd that the special attention code the paper is dedicated to is not used at all. All of it seems to stem off of conv_in.weight modification, the motion_module (which is just finetuned AnimateDiff arch), fps_embedding, and motion_embedding.

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

4 participants