Text-guided generative diffusion models unlock powerful image creation and editing tools. While these have been extended to video generation, current approaches that edit the content of existing footage while retaining structure require expensive re-training for every input or rely on error-prone propagation of image edits across frames. This work presents a structure and content-guided video diffusion model that edits videos based on visual or textual descriptions of the desired output. Conflicts between user-provided content edits and structure representations occur due to insufficient disentanglement between the two aspects. As a solution, we show that training on monocular depth estimates with varying levels of detail provides control over structure and content fidelity. Our model is trained jointly on images and videos, exposing explicit control of temporal consistency through a novel guidance method. Our experiments demonstrate various successes; fine-grained control over output characteristics, customization based on a few reference images, and a strong user preference towards the results by our model.

Leave a Reply

Help us find great AI content


Never miss a thing! Sign up for our AI Hackr newsletter to stay updated.


AI curated tools and resources. Find the best AI tools, reports, research entries, writing assistants, chrome extensions and GPT tools.