Skip to main content
Fordel Studios logoFordel Studios
Start a Conversation
Back to Pulse
TechCrunch

Luma releases a new AI model that lets users generate a video from a start and end frame

Read the full articleLuma releases a new AI model that lets users generate a video from a start and end frame on TechCrunch
↗

What Happened

Luma AI's new model is available through the company's Dream Machine platform.

Our Take

This is in-betweening, which is clever but not what everyone wanted. You've got frame A, frame B, fill the middle—useful for editors, not for "make me a video from text."

The gaming/film angle is real. Shot cleanup, removing jank. But the hype pretends this solves video generation. It doesn't.

Why care? Luma's racing Runway on the video synthesis stack. Whoever gets coherent 2-minute videos from text first wins huge.

What To Do

Start testing Luma's API if you're building video features; they're shipping monthly, and the API will be essential if they win the stack race.

Cited By

React

Loading comments...