HiDream ModelSpec - #371
Open
a-r-r-o-w wants to merge 2 commits into
Open
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes #366
This PR adds support for training HiDream-Image using the Diffusers adaptation. Additionally, take a look at the Diffusers Trainer: huggingface/diffusers#11281
Currently, only the Full and Dev checkpoints are supported:
For training "Fast", extensive testing with timestep schedules (possibly LADD) are required, so it is not going to be covered in this PR.
Full-finetuning may fail even on an 80gb GPU until expert parallel or better load balancing with gradient checkpointing is implemented
Note: This PR is a work-in-progress and may not work as intended yet!