KwaiMind Technical Report

arXiv:2609.26375 · cs.CV · Submitted 2026-09-22 · Read on arXiv

cs.CV

Submitted: 2026-09-22

Updated: 2026-09-29

Comments: KwaiMind Team, Kuaishou Group

Code: https://github.com/KwaiMmu/KwaiMind

License: http://creativecommons.org/licenses/by-nc-nd/4.0/

The gist: Commercial image editing requires product identity preservation, accurate text rendering, and user appeal alongside general editing quality.

Terminology

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.

Sources

Related papers