EditHF-1M: A Million-Scale Rich Human Preference Feedback for Image Editing

TL;DR

This paper introduces EditHF-1M, a large-scale dataset with human preferences for image editing, and develops evaluation and reward models that improve alignment with human judgments and enhance image editing performance.

Contribution

The paper presents a novel million-scale dataset for human preferences in image editing and proposes a multimodal evaluation model and reward framework to improve image editing quality.

Findings

EditHF achieves superior human preference alignment.

Fine-tuning with EditHF-Reward improves image editing models.

The dataset and models enhance evaluation and optimization of image editing.

Abstract

Recent text-guided image editing (TIE) models have achieved remarkable progress, while many edited images still suffer from issues such as artifacts, unexpected editings, unaesthetic contents. Although some benchmarks and methods have been proposed for evaluating edited images, scalable evaluation models are still lacking, which limits the development of human feedback reward models for image editing. To address the challenges, we first introduce \textbf{EditHF-1M}, a million-scale image editing dataset with over 29M human preference pairs and 148K human mean opinion ratings, both evaluated from three dimensions, \textit{i.e.}, visual quality, instruction alignment, and attribute preservation. Based on EditHF-1M, we propose \textbf{EditHF}, a multimodal large language model (MLLM) based evaluation model, to provide human-aligned feedback from image editing. Finally, we introduce \textbf{EditHF-Reward}, which utilizes EditHF as the reward signal to optimize the text-guided image editing models through reinforcement learning. Extensive experiments show that EditHF achieves superior alignment with human preferences and demonstrates strong generalization on other datasets. Furthermore, we fine-tune the Qwen-Image-Edit using EditHF-Reward, achieving significant performance improvements, which demonstrates the ability of EditHF to serve as a reward model to scale-up the image editing. Both the dataset and code will be released in our GitHub repository: https://github.com/IntMeGroup/EditHF.