Add reverse CogVideoX conversion script (HF format -> original format)#13838
Open
TheChyeahhh wants to merge 1 commit into
Open
Add reverse CogVideoX conversion script (HF format -> original format)#13838TheChyeahhh wants to merge 1 commit into
TheChyeahhh wants to merge 1 commit into
Conversation
This script converts HuggingFace Diffusers CogVideoX checkpoints back
to the original CogVideoX format, reversing the transformations in
convert_cogvideox_to_diffusers.py.
Supports:
- Transformer state dict conversion (query_key_value merge, layernorm
list reconstruction, adaLN modulation reconstruction, key renames)
- VAE state dict conversion (up_blocks index reversal, key renames)
Usage:
python scripts/convert_diffusers_to_original_cogvideox.py \
--checkpoint_path /path/to/hf/pipeline \
--output_path /path/to/output
Closes huggingface#10076
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 a script to convert HuggingFace Diffusers CogVideoX checkpoints back to the original CogVideoX format.
Motivation: Issue #10076 asks for reverse conversion scripts. While and already exist for SD/SDXL, there is no reverse script for CogVideoX.
What this does:
Usage:
Closes #10076