Audience
Creators, video editors, content producers, and AI researchers wanting a tool to make realistic, text-driven edits to video without needing manual video masks or deep technical tools
About Lucy Edit AI
Lucy Edit is an open-weight foundation model for text-guided video editing that enables users to apply natural language instructions to videos, no masking, no hand annotations, no external guidance needed. It supports edits such as changing clothing and accessories, replacing characters or objects (e.g., swapping a person with an animal), transforming scenes (style, background, lighting), and making color or style changes, all while preserving the identity of subjects and maintaining motion consistency and realistic appearance across frames. The model is built on the architecture, with a VAE + DiT (diffusion transformer) stack, and designed so that prompts of ~20-30 descriptive words perform best. There’s a free/open version (non-commercial license) plus Pro versions/hosted APIs for more production-oriented use.