Talk2Image: A Multi-Agent System for Multi-Turn Image Generation and Editing

Text-to-image generation tasks have driven remarkable advances in diverse media applications, yet most focus on single-turn scenarios and struggle with iterative, multi-turn creative tasks. Recent dialogue-based systems attempt to bridge this gap, but their single-agent, sequential paradigm often causes intention drift and incoherent edits. To address these limitations, we present Talk2Image, a novel multi-agent system for interactive image generation and editing in multi-turn dialogue scenarios. Our approach integrates three key components: intention parsing from dialogue history, task decomposition and collaborative execution across specialized agents, and feedback-driven refinement based on a multi-view evaluation mechanism. Talk2Image enables step-by-step alignment with user intention and consistent image editing. Experiments demonstrate that Talk2Image outperforms existing baselines in controllability, coherence, and user satisfaction across iterative image generation and editing tasks.

Authors

• Shichao Ma Fuxi AI Lab, NetEase, Inc.
• Yunhe Guo University of Science and Technology of China
• Jiahao Su University of Science and Technology of China
• Qihe Huang University of Science and Technology of China (USTC) Youtu Laboratory, Tencent
• Zhengyang Zhou University of Science and Technology of China
• Yang Wang

Keywords

No keywords are indexed for this paper.