feat: (taehv) support taeh3 - #1874
Merged
Merged
Conversation
Contributor
Author
|
I have managed to get the parallel version of taehv decoding working, but the graph size is scaling with the number of frames... I will try to make it work cleanly without exploding graph size and open another PR. Edit: maybe the larger graph size isn't that bad after all. |
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Support for https://github.com/madebyollin/taehv/blob/main/safetensors/taeh3.safetensors
Related Issue / Discussion
Additional Information
Encoding images tested and works, video decoding works but uses too much memory (OOM on ROCm backend for 2s videos, even with --vae-conv-direct, I think sequential decoding should be implemented to lower the memory requirements. Works on CPU backend for longer videos, but not as quick)
Checklist