To improve human life, AI systems must be able to help us improve the physical world. What stands between us and that prosperous future is the problem of generalization in physical AI.
To solve this problem, we are establishing a new open science physical AI lab at Luma.
Read more → lumalabs.ai/news/luma-open-p…
Have you ever wanted to set one of your coworkers on fire? Well neither had we, but creator Hahn humorously featured three of his teammates in this short featuring a spoof post-race interview.
Made with Luma Ray3.2. Features includes multi-keyframe control, expressive facial performance, HDR EXR outputs, reframe, and motion transfer.
Try it on @LumaLabsAI now.
#luma#ai
"AI can make it. The great idea still has to be human".
Dream Brief, named one of five Cannes contenders for shots by Lora Schulson of 72andSunny.
- shots.net/news/view/cannes-c…
Partnership is the new power move.
Luma is at Cannes Lions 2026 with the partners building the next era of creative work. June 22–26, AI & Tech Sandbox and Luma House. Full schedule below.
RSVP to join us → lumalabs.ai/cannes
Everything created with the @LumaLabsAI agent: characters, worlds, music, SFX, graphics.
Then Ray3.2 brings it to life. Style transfer, character outfit swaps, consistency across every frame, using multi-keyframe for precise timing.
Luma Ray3.2 available now.
Made by: Jacob Russo
Ray 3.2 is the peak of control for high precision - enabling high quality and high scale content
1. Multiple keyframes for precise control over video generation - the most adherent model for keyframe-based controls
2. Highly precise facial expression transfer in video-to-video
3. High quality motion transfer in video-to-video
4. High quality reframe to create new aspect ratios
and many new goodies!
Unveiling the magic behind our Ray3.2 trailer. Out now.
Full control surface and cinematic grade. Direction goes in. Cinema comes out.
@LumaLabsAI Ray3.2 → lumalabs.ai/ray3-2#luma#lumaai
The Ray3.2 API runs cinematic-grade at scale and integrates into the products you already build. Made for developers, agencies, and enterprises building cinema inside the products they ship.
Start building → lumalabs.ai/api
Reframe handles the backdrop. V2V handles the SKU. HDR generation and EXR export handle the mood. One brand system, every market, every format, generated consistently through a single API.
1080p output across the model. V2V at up to 20 seconds. Native HDR Generation and 16-bit EXR export so AI work composites alongside live-action plates in your users' Resolve or Nuke.
Multi-keyframe lets you set up to 16 keyframes inside a single clip. Direct what changes and what holds, beat by beat. Sequence-level control, exposed at the API.
Reframe handles every aspect ratio. Improved motion transfer keeps the choreography. Expressive facial performance preserves the actor's read. One brand system, every market, every format.
Modify Video V2 reshapes footage you already have. Swap the wall, the world, the wardrobe. The lighting holds. The performance survives. Up to 20 seconds, all at 1080p.
Multi-Keyframe lets you set up to 16 keyframes inside a single clip. Direct what changes, what holds, and how the story lands. The shot is yours to compose, frame by frame.
Ray3.2 from @LumaLabsAI is live on fal, day 0.
- Multi-keyframe control
- Expressive facial performance
- HDR EXR outputs
- Reframing motion transfer
And for the first time, the full Ray control surface is available via API.
Warning: this video will unlock new capabilities for your @LumaLabsAI creative agent.
If you’re unsure other ways to use your agent, just ask your agent “My job is _____. What are all the ways I can use you?”
Would love to see what ya’ll come up with! :)
#luma#lumaai#creativeagent
AI meets VFX.
We're moving from editing pixels to directing outcomes. This clip shows how AI can composite and render directly onto video—turning ideas into finished visuals faster than ever. Made with @LumaLabsAI
Full tutorial on our YouTube channel.
Made by: Jack Fishkin
#AI#VFX#Filmmaking