LightningDrag: Lightning Fast and Accurate Drag-based Image Editing Emerging from Videos

Accuracy and speed are critical in image editing tasks. Pan et al. introduced a drag-based framework using Generative Adversarial Networks, and subsequent studies have leveraged large-scale diffusion models. However, these methods often require over a minute per edit and exhibit low success rates. We present LIGHT-NINGDRAG, which achieves high-quality dragbased editing in about one second on general images. By redefining drag-based editing as a conditional generation task, we eliminate the need for time-consuming latent optimization or gradient-based guidance, achieving high-quality editing in <1s. Our model is trained on largescale paired video frames, capturing diverse motion (object translations, pose shifts, zooming, etc.) to significantly improve accuracy and consistency. Despite being trained only on videos, our model generalizes to local deformations beyond the training data (e.g., lengthening hair, twisting rainbows). Extensive evaluations confirm the superiority of our approach. The code and model are available at https://github.com/magicresearch/LightningDrag .