Luma AI builds multimodal generative models for video and image synthesis. The Ray model family (currently Ray3/Ray3.14) supports text-to-video, image-to-video, and video-to-video with reasoning-driven generation, native 1080p, and a first-to-market HDR pipeline with 16-bit EXR export. The Photon family covers image generation. Inference is API-accessible via the Dream Machine platform.
Luma AI's Ray3.14 brings native 1080p video generation to Dream Machine at 4x the speed and one-third the cost of its predecessor, removing the core trade-off between quality and scale in professional AI video.