Most AI video tools are generation machines: you type a prompt, wait, and hope the output is close to what you imagined. Runway's Aleph 2.0 flips that model entirely. Instead of generating from scratch, it takes footage you already have and rewrites only the parts you point it to , leaving everything else exactly as it was.
One frame to rule them all
Aleph 2.0 is an upgrade to Runway's flagship in-context video editing model. Edit one frame and Aleph 2.0 modifies the rest of your video to match, preserving everything you didn't ask to change. The key word here is in-context , the model reads the scene's existing lighting, motion, and object structure before making any change, rather than hallucinating a new scene from a text description.
In the new Edit Studio interface, users can select any single frame from a video clip, make changes to it using prompts or direct adjustments, preview the result immediately, and then allow the model to propagate the edit consistently across the entire sequence. That preview step is a bigger deal than it sounds: it reduces one of AI video's most expensive failure modes , waiting for a full generation just to discover that the model interpreted the request differently than intended.
What's actually new
Aleph 2.0 is an upgrade to Runway's flagship video editing model, launching alongside Edit Studio , a new product experience designed to close the gap between the video you have and the video you actually need. The upgrade ships four concrete improvements:
- Longer clips:
Don't miss what's next in AI
Join 300,000+ engineers and researchers who get the signal, not the noise.
- Full access to in-depth AI research breakdowns
- Be the first to know what's trending before it hits mainstream
- Daily curated papers, repos, and industry moves