Feat: support Chroma Radiance x0 #1091
Open
+62
−6
Conversation
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Outdated suggestions cannot be applied.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.
https://huggingface.co/lodestones/Chroma1-Radiance/tree/main
https://huggingface.co/stduhpf/Chroma1-Radiance-gguf/tree/main
Lastest versions of Chroma Radiance use x0-prediction instead of the default Flux eps-prediction.
I also tried to add support for the "latest_x0_experimental_patch_32" model, it seems to consistently blow up after a couple steps. (first few steps look fine with preview)
EDIT: Found a way to make it more stable, but it's not great either
Empty tensors were causing crashes (GGML_ASSERT in gguf.c) when trying to convert the models, I've added a workaround so we can convert it.