Dreamix: Video Diffusion Models are General Video Editors
Abstract: Text-driven image and video diffusion models have recently achieved unprecedented generation realism. While diffusion models have been successfully applied for image editing, few can edit motion in video. We present a diffusion-based method that is able to perform text-based motion and appearance editing of general, real-world videos. Our approach uses a video diffusion model to combine, at inference time, the low-resolution spatio-temporal information from the original video with new, high resolution information that it synthesized to align with the guiding text prompt. As maintaining high-fidelity to the original video requires retaining some of its high-resolution information, we add a preliminary stage of finetuning the model on the original video, significantly boosting fidelity. We propose to improve motion editability by using a mixed objective that jointly finetunes with full temporal attention and with temporal attention masking. We extend our method for animating images, bringing them to life by adding motion to existing or new objects, and camera movements. Extensive experiments showcase our method's remarkable ability to edit motion in videos.
Submission Length: Regular submission (no more than 12 pages of main content)
Assigned Action Editor: ~Zhe_Gan1
Submission Number: 2447
Loading