Wan 2.1 T2V training #1348
Merged
Wan 2.1 T2V training #1348
Conversation
This file contains 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
added 9 commits
March 22, 2025 11:43
…good idea to run it
…uner into feature/wan-2.1-t2v
mhirki
reviewed
Mar 23, 2025
added 20 commits
March 23, 2025 06:48
…k this value and do not apply it for unrelated models
|
well, quanto fp8 doesn't work, but now on pytorch 2.6 and the new torchao, we have fp8-torchao working pretty well on LTXVideo and Wan 2.1. |
added 7 commits
March 24, 2025 01:48
…, and things seem to work better now
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
The 1.3B T2V model doesn't seem to work correctly in Diffusers, or, is just really bad.
I'm not sure. Some people like it, they'll train it for images. I haven't gotten any good results from it.