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

TL;DR

Talk2Image is a multi-agent system that enables coherent, multi-turn image generation and editing through intention parsing, task decomposition, and collaborative refinement, improving controllability and user satisfaction.

Contribution

It introduces a novel multi-agent framework for interactive, multi-turn image editing that addresses intention drift and incoherence in existing dialogue-based systems.

Findings

Outperforms baselines in controllability and coherence

Enhances user satisfaction in iterative editing tasks

Enables step-by-step alignment with user intentions

Abstract

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.