Fix Qwen3-VL normalization: use 0.5/0.5/0.5 from checkpoint#105
Open
stikves wants to merge 3 commits into
Open
Fix Qwen3-VL normalization: use 0.5/0.5/0.5 from checkpoint#105stikves wants to merge 3 commits into
stikves wants to merge 3 commits into
Conversation
The qwen3-vl VLMSpec hardcoded OpenAI-CLIP normalization stats, but Qwen3-VL checkpoints specify image_mean=image_std=[0.5, 0.5, 0.5]. This caused a silent ~1.86x overscale on every pixel fed to the vision encoder. Fixes apple#82.
stikves
requested review from
alejandro-isaza,
carinapeng,
kevchengcodes and
tjia1818
tjia1818
approved these changes
Jul 15, 2026
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The qwen3-vl VLMSpec hardcoded OpenAI-CLIP normalization stats, but Qwen3-VL checkpoints specify image_mean=image_std=[0.5, 0.5, 0.5]. This caused a silent ~1.86x overscale on every pixel fed to the vision encoder.
Fixes #82.
Tested locally. Now it identifies background colors more correctly.