HarmonPaint: Harmonized Training-Free Diffusion Inpainting
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Image InpaintingSimilar Papers 제목 키워드 기반
Lanpaint: Training-Free Diffusion Inpainting with Exact and Fast Conditional Inference
Diffusion models generate high-quality images but often lack efficient and universally applicable inpainting capabilities, particularly in community-trained models. We introduce LanPaint, a training-free method tailored …
VipDiff: Towards Coherent and Diverse Video Inpainting via Training-free Denoising Diffusion Models
Recent video inpainting methods have achieved encouraging improvements by leveraging optical flow to guide pixel propagation from reference frames either in the image space or feature space. However, they would produce s…
DenoisingImage InpaintingOptical Flow EstimationVideo InpaintingIS-Diff: Improving Diffusion-Based Inpainting with Better Initial Seed
Diffusion models have shown promising results in free-form inpainting. Recent studies based on refined diffusion samplers or novel architectural designs led to realistic results and high data consistency. However, random…
InpaintSLat: Inpainting Structured 3D Latents via Initial Noise Optimization
We present a training-free approach for controllable 3D inpainting based on initial noise optimization. In the structured 3D latent diffusion framework, we observe that the underlying geometric structure is established d…
Training-free Geometric Image Editing on Diffusion Models
We tackle the task of geometric image editing, where an object within an image is repositioned, reoriented, or reshaped while preserving overall scene coherence. Previous diffusion-based editing methods often attempt to …
Image Editing