you're not talking to someone who woke up a loser
ceo @LumaLabsAI working on multimodal AGI | prev: built Vision Pro at | everything is figureoutable
We are launching a new Open Physical AI Lab to solve the generalization in robotics. Discussion with @CarolineHydeTV and @EdLudlow on Bloomberg Tech this morning -
Image-to-video is at the core of storytelling with generative video. Images are the lights and camera; the video model brings the action. Until now, image-to-video has been an afterthought in all video models. Like, there was barely any action. That changes today!
Ray2
Image to Video with #Ray2 is here. Drop any image into Dream Machine to make it a video and bring it to life — from historic artifacts and paintings to memes, custom art and photos of any kind. Available now.
Today with Ray2 Flash we are introducing a new method of distilling frontier models that retains all their capabilities and ultra high quality -- at 500% higher efficiency! (we are using some gains to offer higher throughput so users have shorter queues) Our team has been
Introducing #Ray2 Flash—3x faster, 3x cheaper new model. Flash brings Ray’s frontier production-ready Text-to-Video, Image-to-Video, audio, and control capabilities with high quality and speed to all subscribers—so you can create more, faster, and without limits. Available now.
Ray2 represents a GPT2 to GPT3 level jump for video models. And now it is available in the Luma API!
Getting close to production quality footage from an API means video models become increasingly more suitable as programming primitives for a new era of multimedia apps.
The Ray2 API is here. Developers can now build and scale creative products with our most advanced video generation model yet. From cinematic realism to dynamic motion, the possibilities are limitless. Start building today lumalabs.ai/dream-machine/….
As we make 3D ubiquitous, we will be able to show and communicate things about the world in the medium of our reality. This took OP 2hrs!
"The original poster (OP) 3D scanned their hometown using a drone, LumaAI software, and Unreal Engine. They then simulated rising sea levels
Today we are introducing Ray2! Scaling pretraining by 10x on a novel efficient architecture, we are able to unlock the next frontier in video generation - fast natural coherent motion and physics. This skyrockets the success rate of usable production-ready generations and makes
Introducing Ray2, a new frontier in video generative models. Scaled to 10x compute, #Ray2 creates realistic videos with natural and coherent motion, unlocking new freedoms of creative expression and visual storytelling. Available now. Learn more lumalabs.ai/ray.
