Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

CDST: Color Disentangled Style Transfer for Universal Style Reference Customization

About

We introduce Color Disentangled Style Transfer (CDST), a novel and efficient two-stream style transfer training paradigm which completely isolates color from style and forces the style stream to be color-blinded. With one same model, CDST unlocks universal style transfer capabilities in a tuning-free manner during inference. Especially, the characteristics-preserved style transfer with style and content references is solved in the tuning-free way for the first time. CDST significantly improves the style similarity by multi-feature image embeddings compression and preserves strong editing capability via our new CDST style definition inspired by Diffusion UNet disentanglement law. By conducting thorough qualitative and quantitative experiments and human evaluations, we demonstrate that CDST achieves state-of-the-art results on various style transfer tasks.

Shiwen Zhang, Zhuowei Chen, Lang Chen, Yanze Wu• 2025

Related benchmarks

TaskDatasetResultRank
Style TransferStyle reference + prompt scenario
Prompt Alignment (CLIP Score)0.291
7
Stylized Image GenerationUser Study Style/Color Ref + Prompt
Prompt Alignment91
6
Characteristics-preserved style transferUser Study
Style Similarity63.2
1
Style and Color Transfer with Content ReferenceUser Study Style/Color Ref + Content Ref
Style Similarity78
1
Showing 4 of 4 rows

Other info

Follow for update