DiffEditor: Boosting Accuracy and Flexibility on Diffusion-based Image Editing
This work addresses challenges in precise and flexible image editing for users of text-to-image diffusion models, representing an incremental improvement over existing methods.
The paper tackles the problem of fine-grained image editing with diffusion models, where existing methods often lack accuracy and flexibility in complex scenarios; the proposed DiffEditor method achieves state-of-the-art performance on various editing tasks by introducing image prompts, combining SDE with ODE sampling, and using gradient guidance and time travel strategies.
Large-scale Text-to-Image (T2I) diffusion models have revolutionized image generation over the last few years. Although owning diverse and high-quality generation capabilities, translating these abilities to fine-grained image editing remains challenging. In this paper, we propose DiffEditor to rectify two weaknesses in existing diffusion-based image editing: (1) in complex scenarios, editing results often lack editing accuracy and exhibit unexpected artifacts; (2) lack of flexibility to harmonize editing operations, e.g., imagine new content. In our solution, we introduce image prompts in fine-grained image editing, cooperating with the text prompt to better describe the editing content. To increase the flexibility while maintaining content consistency, we locally combine stochastic differential equation (SDE) into the ordinary differential equation (ODE) sampling. In addition, we incorporate regional score-based gradient guidance and a time travel strategy into the diffusion sampling, further improving the editing quality. Extensive experiments demonstrate that our method can efficiently achieve state-of-the-art performance on various fine-grained image editing tasks, including editing within a single image (e.g., object moving, resizing, and content dragging) and across images (e.g., appearance replacing and object pasting). Our source code is released at https://github.com/MC-E/DragonDiffusion.