FreeDiff: Progressive Frequency Truncation for Image Editing with Diffusion Models

arXiv:2404.11895v1 Announce Type: new
Abstract: Precise image editing with text-to-image models has attracted increasing interest due to their remarkable generative capabilities and user-friendly nature. However, such attempts face the pivotal challenge of misalignment between the intended precise editing target regions and the broader area impacted by the guidance in practice. Despite excellent methods leveraging attention mechanisms that have been developed to refine the editing guidance, these approaches necessitate modifications through complex network architecture and are limited to specific editing tasks. …

abstract arxiv capabilities challenge cs.cv diffusion diffusion models editing face generative guidance however image nature pivotal practice text text-to-image type