LGCC: Enhancing Flow Matching Based Text-Guided Image Editing with Local Gaussian Coupling and Context Consistency
This addresses efficiency and quality issues in text-guided image editing for users of multimodal models, though it builds incrementally on existing methods like BAGEL.
The paper tackles limitations in flow matching-based text-guided image editing (like detail degradation and inefficiency) by proposing LGCC with Local Gaussian Noise Coupling and Content Consistency Loss, achieving a 1.60% improvement in local detail scores and 2x-5x speedup while reducing inference time by 40%-50%.
Recent advancements have demonstrated the great potential of flow matching-based Multimodal Large Language Models (MLLMs) in image editing. However, state-of-the-art works like BAGEL face limitations, including detail degradation, content inconsistency, and inefficiency due to their reliance on random noise initialization. To address these issues, we propose LGCC, a novel framework with two key components: Local Gaussian Noise Coupling (LGNC) and Content Consistency Loss (CCL). LGNC preserves spatial details by modeling target image embeddings and their locally perturbed counterparts as coupled pairs, while CCL ensures semantic alignment between edit instructions and image modifications, preventing unintended content removal. By integrating LGCC with the BAGEL pre-trained model via curriculum learning, we significantly reduce inference steps, improving local detail scores on I2EBench by 1.60% and overall scores by 0.53%. LGCC achieves 3x -- 5x speedup for lightweight editing and 2x for universal editing, requiring only 40% -- 50% of the inference time of BAGEL or Flux. These results demonstrate LGCC's ability to preserve detail, maintain contextual integrity, and enhance inference speed, offering a cost-efficient solution without compromising editing quality.