AI Paper Atlas

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

HP-Edit: A Human-Preference Post-Training Framework for Image Editing

Fan Li, Chonghuinan Wang, Lina Lei, Yuping Qiu, Jiaqi Xu, Jiaxiu Jiang, Xinran Qin, Zhikai Chen, Fenglong Song, Zhixin Wang, Renjing Pei, Wangmeng Zuo

CVPR 2026 · Image generation › Text-to-image diffusion · approach: Preference optimization for diffusion · 2 citations (OpenAlex)

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
post-train with HP-EditQwen-Image-Edit-2509 · RealPref-BenchHP-score (overall): 4.472 -> 4.667Improved
post-train with HP-Edit (relighting task)Qwen-Image-Edit-2509 · RealPref-Bench (Relighting)HP-score: 3.54 -> 3.913Improved
train with unfiltered BaseData and basic scorer (ablation)Qwen-Image-Edit-2509 · RealPref-BenchHP-score (overall): 4.472 -> 4.391Hurt
filter out score-5 cases (RealPref-50K) instead of raw BaseData (ablation)HP-Edit with Base-Scorer · RealPref-BenchHP-score (overall): 4.391 -> 4.577Improved
add task-specific HP-Scorer instead of basic scorer (ablation)HP-Edit with RealPref-50K · RealPref-BenchHP-score (overall): 4.577 -> 4.667Improved
increase LoRA rank from 8 to 32 (ablation)HP-Edit · RealPref-BenchHP-score (overall): 4.614 -> 4.667Improved
increase LoRA rank from 32 to 128 (ablation)HP-Edit · RealPref-BenchHP-score (overall): 4.667 -> 4.645No clear effect
use online GRPO with HP-Scorer instead of offline DPO (ablation)HP-Edit · RealPref-BenchHP-score (overall): 4.521 -> 4.590Improved
apply HP-Edit post-trainingQwen-Image-Edit-2509 · GEdit-Bench-ENG_O: 7.54 -> 8.30Improved
apply HP-Edit post-trainingQwen-Image-Edit-2509 · DreamBench++CP times PF: 0.575 -> 0.630Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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