Hyper SDXL Lora support #127
Merged
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
anfals
reviewed
Oct 30, 2024
|
|
||
| @classmethod | ||
| @validate_hf_hub_args | ||
| def lora_state_dict(cls, pretrained_model_name_or_path: str, **kwargs): |
There was a problem hiding this comment.
nit: I think calling this something like get_lora_state_dict might be clearer about what the method is doing?
anfals
previously approved these changes
Oct 30, 2024
There was a problem hiding this comment.
I'm mostly just skimming this file since it seems to just be a lot of wrangling of PyTorch state_dict to Flax. Someone who works more on MaxDiffusion might have more thoughts
anfals
approved these changes
Oct 31, 2024
| @@ -26,4 +26,6 @@ git+https://github.com/mlperf/logging.git | |||
| opencv-python-headless==4.10.0.84 | |||
| orbax-checkpoint>=0.5.20 | |||
| tokenizers==0.20.0 | |||
| huggingface_hub==0.24.7 | |||
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Outdated suggestions cannot be applied.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 establishes LoRA support and includes Hyper-SD XL LoRA loading for inference.