ByteDance/AnimateDiff-Lightning text2vid support #54
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
This commit introduces issue templates to streamline the submission process for bug reports and feature requests. With these templates in place, contributors will have clear guidance on how
This commit updates the issue templates config file so that the discord link description is improved.
This commit fixes some yaml syntax errors.
This commit fixes the ISSUE templates config.
|
Sloppy code, but the motion LoRas are pretty neat |
|
Note: this model seems to fall apart when generating longer videos. About 16 frames seems good. There is also a regular AnimateDiff, which should be able to hook into any (SD based) text2img model (there's a separate one for SDXL based text2img). It's much slower, but I've seen some really nice results coming out of that. |
This commit ensures that the model is pre-traced when SFAST is enabled for the ImageToVideo pipeline. Without this pre-tracing the first request will be slower than a non SFAST call.
This commit updates the development documentation to ensure that the right vscode config is used.
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Outdated suggestions cannot be applied.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.
Builds on #51 to add the
ByteDance/AnimateDiff-Lightningmodel.Works, but models seems very VRAM hungry. Also getting minutes of inference time vs <!0 seconds of their demo, so something needs to be finetuned.