AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Style-GRPO: Semantic-Aware Preference Optimization for Image Style Transfer Guided by Reward Modeling

Jianbin Zhao, Chaoran Feng, Miao Yu, Yingtao Li, Zhenyu Tang, Wangbo Yu, Yian Zhao, Xiaomin Li, Li Yuan, Yonghong Tian

CVPR 2026 · Image generation › Text-to-image diffusion · approach: Preference optimization for diffusion

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add SFT on StyleReward-Dataset to FLUX.1 Kontext (ablation)FLUX.1 Kontext · ImgEdit (GPT-4o)score: 4.55 -> 4.67Improved
add GRPO post-training with StyleScore directly to FLUX.1 Kontext (no SFT) (ablation)FLUX.1 Kontext · ImgEdit (GPT-4o)score: 4.55 -> 4.68Improved
add GRPO post-training after SFT (ablation)SFT model · ImgEdit (GPT-4o)score: 4.67 -> 4.74Improved
add GRPO post-training after SFT (ablation)SFT model · ImgEdit (Gemini-2.5-Pro)score: 4.34 -> 4.46Improved
add SFT before GRPO instead of GRPO only (ablation)Style-GRPO · StyleReward-Dataset benchmark (StyleScore)StyleScore: 3.85 -> 3.91Improved
add GRPO only (no SFT) versus SFT only on Gemini judge (ablation)FLUX.1 Kontext · ImgEdit (Gemini-2.5-Pro)score: 4.29 -> 4.30No clear effect
train StyleScore reward model on StyleReward-Dataset instead of using general VLMQwen2.5-VL-7B reward model · 500 test pairspreference accuracy: 65.2% -> 98.6%Improved
apply Style-GRPO to FLUX.1 KontextFLUX.1 Kontext · AnyEdit global style transferL1 distance: 0.2457 -> 0.0944Improved
apply Style-GRPO to FLUX.1 KontextFLUX.1 Kontext · AnyEdit global style transferCLIPtext: 0.1857 -> 0.1664Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy