LiveEdit is a streaming video editing framework for causal, frame-by-frame diffusion editing with real-time responsiveness. It aims to preserve backgrounds and non-edited regions while applying local or global text-guided changes as a video arrives, rather than waiting for a full offline sequence.
The system uses a three-stage distillation pipeline: foundation tuning gives a bidirectional diffusion transformer editing ability, causal adaptation converts it to chunk-wise streaming attention, and DMD distillation compresses generation to four diffusion steps. An autoregressive-oriented mask cache reuses tokens from unchanged regions to reduce redundant computation.
LiveEdit is useful for interactive video effects, creative tools, virtual production, and low-latency visual editing research. The project reports 12.66 FPS streaming inference and provides code, comparison galleries, and examples such as changing fur, lighting, clothing, sky, and other scene attributes while maintaining temporal continuity.
Get more likes & reach the top of search results by adding this button on your site!
Get top updates in AI to your inbox every weekend. It's free!