Kandinsky5 model support #10988
Open
Kandinsky5 model support #10988
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Contributor
Author
|
+label: Core |
lite and pro T2V tested to work
Default values are too weak for any meaningful changes, these should probably be exposed as advanced node options when that's available.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Adds support for Kandinsky5 -family video and image models.
Model code is refactored to be more in line with models I'm used to work with, and optimized for lower peak VRAM consumption.
I took the liberty of including RoPE and FFN chunking I've been testing, as it had rather big benefits at the higher input sizes these models support, namely the 241 frames for the 10s models, chunking dropped peak VRAM usage by:
Speed differences were within margin of error. Chunking is currently enabled based on sequence length.