Fix DreamLite legacy block type aliases#14066
Open
ElectricGoal wants to merge 1 commit 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What does this PR do?
Fixes #14065.
carlofkl/DreamLite-basesaves DreamLite UNet block type names using upstream-style strings such asCrossAttnDownRemoveSelfAttnBlock2D,CrossAttnUpBlock2D, andCrossAttnUpRemoveSelfAttnBlock2DV1.DreamLiteUNetModelcurrently only accepts the DreamLite-local class names, soDreamLitePipeline.from_pretrained("carlofkl/DreamLite-base")fails while constructing the UNet.This PR adds a small alias normalization step in the DreamLite block dispatch helpers so those saved config values map to the existing DreamLite block classes. It also adds a focused regression test using the exact block strings from the public
checkpoint config.
Coordination issue: #14065
Before submitting
.ai/review-rules.md?Tests
Who can review?
Pipelines and models: @Carlofkl