From Competition to Coopetition: Coopetitive Training-Free Image Editing Based on Text Guidance

2026-04-17

AI Summary

Existing training-free, text-guided image editing methods suffer from a lack of coordination between editing and reconstruction branches due to their adversarial paradigm, leading to semantic conflicts and unpredictable outcomes. This work proposes CoEdit, a novel framework that introduces a cooperative-competitive mechanism: it employs dual-entropy attention manipulation in the spatial domain to precisely localize editable regions and incorporates an entropy-based latent refinement mechanism in the temporal domain to dynamically optimize latent representations and suppress error accumulation. Additionally, a fidelity-constrained editing scoring scheme enhances structural consistency. Without requiring any additional training, CoEdit significantly improves editing quality, semantic fidelity, and text-image alignment on standard benchmarks, enabling more controllable and consistent zero-shot image editing.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Text-guided image editing, a pivotal task in modern multimedia content creation, has seen remarkable progress with training-free methods that eliminate the need for additional optimization. Despite recent progress, existing methods are typically constrained by a competitive paradigm in which the editing and reconstruction branches are independently driven by their respective objectives to maximize alignment with target and source prompts. The adversarial strategy causes semantic conflicts and unpredictable outcomes due to the lack of coordination between branches. To overcome these issues, we propose Coopetitive Training-Free Image Editing (CoEdit), a novel zero-shot framework that transforms attention control from competition to coopetitive negotiation, achieving editing harmony across spatial and temporal dimensions. Spatially, CoEdit introduces Dual-Entropy Attention Manipulation, which quantifies directional entropic interactions between branches to reformulate attention control as a harmony-maximization problem, eventually improving the localization of editable and preservable regions. Temporally, we present Entropic Latent Refinement mechanism to dynamically adjust latent representations over time, minimizing accumulated editing errors and ensuring consistent semantic transitions throughout the denoising trajectory. Additionally, we propose the Fidelity-Constrained Editing Score, a composite metric that jointly evaluates semantic editing and background fidelity. Extensive experiments on standard benchmarks demonstrate that CoEdit achieves superior performance in both editing quality and structural preservation, enhancing multimedia information utilization by enabling more effective interaction between visual and textual modalities. The code will be available at https://github.com/JinhaoShen/CoEdit.

Problem

• text-guided image editing
• training-free
• semantic conflict
• attention control
• coopetition

Innovation

• Coopetitive Editing
• Training-Free Image Editing
• Dual-Entropy Attention
• Entropic Latent Refinement
• Text-Guided Image Manipulation