HarmonPaint: Harmonized Training-Free Diffusion Inpainting
This addresses the need for efficient and coherent inpainting methods for image editing applications, though it appears incremental as it builds on existing diffusion models.
The paper tackled the problem of image inpainting requiring extensive retraining and struggling with coherence, and introduced HarmonPaint, a training-free framework that integrates with diffusion models to achieve high-quality, harmonized inpainting without training.
Existing inpainting methods often require extensive retraining or fine-tuning to integrate new content seamlessly, yet they struggle to maintain coherence in both structure and style between inpainted regions and the surrounding background. Motivated by these limitations, we introduce HarmonPaint, a training-free inpainting framework that seamlessly integrates with the attention mechanisms of diffusion models to achieve high-quality, harmonized image inpainting without any form of training. By leveraging masking strategies within self-attention, HarmonPaint ensures structural fidelity without model retraining or fine-tuning. Additionally, we exploit intrinsic diffusion model properties to transfer style information from unmasked to masked regions, achieving a harmonious integration of styles. Extensive experiments demonstrate the effectiveness of HarmonPaint across diverse scenes and styles, validating its versatility and performance.