Text to video pipeline #187
Open
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 was referenced Sep 4, 2024
e23e726
to
ad46b3c
Compare
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Outdated suggestions cannot be applied.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.
This PR adds support for a
text-to-videopipeline using the THUDM/CogVideoX-2b and THUDM/CogVideoX-5b modelsSome notes:
dl_checkpoints.shscript was modified to download both models, but without any--include "*.fp16.safetensors"argument, as there does not seem to be avariantfor them. I currently do force the precision usingtorch_dtype: FP16 forTHUDM/CogVideoX-2band BF16 forTHUDM/CogVideoX-5bnum_framesparameter is currently hardcoded to their recommended value of49enable_slicing,enable_tiling), we might want to play around with theseSafety checker?Was added by @ad-astra-videoDependent on livepeer/go-livepeer#3161