Mini toolsOverview
Make-A-Video is Meta’s research model that turns text or a reference image into short, coherent video clips using diffusion with space-time attention.
Description
Make-A-Video adapts high-quality text-to-image diffusion to video by adding temporal layers that keep frames consistent as motion unfolds. It learns visual concepts from image–text data and learns movement from unlabeled video, so it can
About Facebook
We're connecting people to what they care about, powering new, meaningful experiences, and advancing the state-of-the-art through open research and accessible tooling.
Location:
Orlando, California, US
Website:
ai.facebook.com
Related Models
Last updated: October 8, 2025
