fix: round latent dimensions up to 8#1
Merged
Conversation
Use 16-pixel dimension alignment in both backend and frontend calculations, and derive target size from aligned output dimensions.
Update expected dimensions for 16-pixel alignment and add frontend regression tests for aligned target derivation and half-even rounding parity.
Document output, expected target, actual target, and rounding differences for all QuickLatent size combinations. Include API E2E size verification outputs.
Use 8-pixel ceil alignment for backend and frontend dimension calculations so scaled targets do not undershoot the selected preset target.
Update dimension expectations for 8-pixel ceil alignment and verify frontend target previews do not undershoot preset targets.
Regenerate the readable size tables and ComfyUI API E2E verification data for 8-pixel ceil alignment.
Zhen-Bo
changed the title
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Round QuickLatent sampler dimensions up to 8-pixel boundaries and document the expected vs actual target sizes for v1.1.0.
Changes
Verification
pytest -q-> 399 passednpm test-> 17 passedImpact
Breaking changes: None
User-facing changes: QuickLatent output dimensions now use 8-pixel ceil alignment, and the Target Size display reflects aligned output multiplied by scale.
Migration required: None