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

Bringing back imaginary friends at @dreamlabla with @lumalabsai Ray 3.2 multi-keyframe modify video 😄🦄

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

Just riffing with @LumaLabsAI Ray 3.2 at @DreamLabLA

Let him cook... @LumaLabsAI Ray3.2 available now → lumalabs.ai/ray3-2

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

Our newest tool uses new motion transfer systems for more versatile and powerful control capabilities. You can use as many keyframes as you like so your ability to control a scene really comes down to your ability to drive motion and edit images. @LumaLabsAI @DreamLabLA

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

We are launching Open Physical AI Lab at Luma to solve generalization in robotics We believe general physical AI is the most consequential problem to solve to improve life on Earth. Allowing one or very few companies to control the entire intelligence and physical infrastructure of the world is a profound threat to the world. This is the path LLMs took, and it is the path physical AI is on today. To solve this problem of generalization in physical AI and to maximally benefit all of humanity, we are establishing the Open Science Physical AI Lab (OPAL Lab) at Luma. Today, physical AI and robotics are in the pre-AI-scale era. Unlike LLMs and multimodal models which are capable of solving a wide range of previously seen and unseen problems, robots are trained on and can only replay specific tasks in specific environments from small scale examples, limiting their utility. Physical AI has a data gap, creating a generalization crisis. The default solution is to simply scale teleoperation to capture data across every possible task and combination of tasks – a physically and economically impossible approach. Over the past 4 years, through fundamental research on multimodal AI, Luma has trained frontier foundation models in 3D, image, video, and unified language-visual generation. In this process, we have built vast infrastructure to make sense of raw internet-scale multimodal data and train efficient generative models with it. Building these systems has given us unique insights into how raw multimodal data can be used to learn physics, perception, reasoning and interaction with the physical world. Over the past few months, mounting empirical evidence from our work on Unified Models has turned this realization into a strong scientific conviction. Generalization is not unique to text. The Open Physical AI Lab will research and scale methods to solve generalization and develop World Models for understanding and interaction with the physical world. This generalization will lead to robot systems proliferating everywhere - factories, research labs, hospitals, streets, and even our homes. Given the societal and economic upside, this transition will be faster than any other technology in history and these systems will be embedded into every layer of human life. Physical AI will help us solve labor shortage and stagnation plaguing world economies. Physical AI will become the means of production in every nation. Allowing one or very few companies to control the entire intelligence and physical infrastructure of the world is a profound threat to humanity and democratic freedom. This is the path LLMs took, and it is the path physical AI is on today. To reverse this trajectory, this lab will be an open science effort. We will use our scale and expertise to build the substrate and make it available so that any dedicated group of people can use it, modify it, and assemble it into systems of productive work. To accelerate progress, we will collaborate with our peer labs and academia on core research, build evaluations to measure progress and assess safety, and partner with industry leaders on chips, hardware, and physical agent systems. If you share this conviction and believe that this foundation should be built in the open for the benefit of all humanity, please come work with us.

Luma Agents can now generate with Seedance 2.0. Point your next project at it, see what it produces, keep moving. Same workflow, more to work with. Open Luma Agents → lumalabs.ai/app

POV: you don’t know how to code, but your AI squirrel is already running around in-game. Steps: Create a @LumaLabsAI animated the character. Luma Agent turned it into a Lottie file. Claude connected everything together. Honestly kinda wild this works. Create by: Jieyi Lee @jieyijeee

Frog Game Devlog 3: From concept to playable character, we turned our @LumaLabsAI generated frog into a fully animatable game asset. This establishes our entire character art pipeline from start to finish. Created by Blake Johnson

Easy facial performance capture with Uni-1 PBR and modify video workflow in @LumaLabsAI! AI integrated Workflow that can play a role in the creation process. Created by: Tony Hou @TonyHouart

I made a game with hand tracking directly in your browser. Pinch to jump. Open your other hand to change the season. Episode 1 of a mini-series on how I did it with @LumaLabsAI and Cursor. If I can do this, so can you. 🐿️🎮 Created by: Jieyi Lee @jieyijeee

Introducing the Uni-1.1 API. It reasons through briefs, not just tokens. First-pass results that actually ship. No middleware, no prompt engineering required. Fashion tools. Architecture renderers. Manga pipelines. Cinematic quality across every vertical. Intelligence you can direct. Aesthetic you can ship. → lumalabs.ai/api

Uni-1.1 API is now live and creates a new pareto frontier - thinking images at the cost and efficiency of old school diffusion models. Uni-1.1 is a model designed for professional work, which continues to be difficult to capture in public benchmarks. Give it a try in Luma or your favorite genai tool! incredibly proud of the Luma team for reaching the frontier and there's a lot more to come!