KwaiMind Technical Report

2026-09-22

AI Summary

该研究通过结合多模态扩散变换器和在线强化学习等技术，开发了KwaiMind系统以解决商业图像编辑中产品识别、文本渲染等问题，并在多项测试中取得最佳成绩。

Abstract

Commercial image editing requires product identity preservation, accurate text rendering, and user appeal alongside general editing quality. We present KwaiMind, an image editing system combining general capabilities with e-commerce specialization. An agent-based data engine maintains approximately 1.8 million high-quality editing pairs. Built on a multimodal diffusion transformer, KwaiMind undergoes continued pre-training and supervised fine-tuning, followed by preference optimization and online reinforcement learning. A general-purpose vision-language judge and specialized rewards for click-through rate (CTR), text rendering, and product consistency guide specialized policies, which are consolidated through on-policy distillation. We introduce Ecom-Bench, covering 11 commercial editing tasks with task-specific visual evaluation and CTR-based ranking. KwaiMind achieves the strongest overall scores among evaluated open-source editors on ImgEdit, GEdit, both language splits of REDEdit, and Ecom-Bench visual quality, and the highest aggregate CTR ranking score among compared systems. Offline, CTR-guided optimization increases the proportion of generated images whose predicted CTR exceeds that of the original product image from 12.16% to 37.41%. In an online A/B experiment, CTR-based selection of product main images yields an approximately 2.44% relative increase in actual CTR. These results demonstrate the value of domain-specific data and reward-driven alignment for commercial image editing.

Problem

• commercial image editing
• product identity preservation
• text rendering
• user appeal

Innovation

• multimodal diffusion transformer
• continued pre-training and supervised fine-tuning
• Ecom-Bench
• CTR-based optimization
• on-policy distillation