GoodDrag: Towards Good Practices for Drag Editing with Diffusion Models
This work addresses a specific issue in image editing for users of diffusion models, offering incremental improvements in stability and quality.
The paper tackles the problem of instability and poor image quality in drag editing with diffusion models by introducing GoodDrag, which alternates between drag and denoising operations and uses an information-preserving motion supervision, resulting in improved fidelity and artifact reduction as demonstrated in experiments against state-of-the-art methods.
In this paper, we introduce GoodDrag, a novel approach to improve the stability and image quality of drag editing. Unlike existing methods that struggle with accumulated perturbations and often result in distortions, GoodDrag introduces an AlDD framework that alternates between drag and denoising operations within the diffusion process, effectively improving the fidelity of the result. We also propose an information-preserving motion supervision operation that maintains the original features of the starting point for precise manipulation and artifact reduction. In addition, we contribute to the benchmarking of drag editing by introducing a new dataset, Drag100, and developing dedicated quality assessment metrics, Dragging Accuracy Index and Gemini Score, utilizing Large Multimodal Models. Extensive experiments demonstrate that the proposed GoodDrag compares favorably against the state-of-the-art approaches both qualitatively and quantitatively. The project page is https://gooddrag.github.io.