Luma Dream Machine
Luma AI · June 2024
● activeClosedvideoAPI Available
Description
Luma AI's video generation model with strong 3D spatial understanding, capable of generating physically consistent video content from text or image prompts. Its 3D-aware generation produces more realistic camera movements and object interactions than purely 2D diffusion approaches.
Key Innovations
Text-to-Video
Text-to-VideoGenerating video clips from text descriptions — one of the newest and most compute-intensive AI capabilities.
Diffusion
DiffusionGenerates outputs by gradually denoising random noise into coherent images/audio. The backbone of Stable Diffusion and DALL·E.
3d-aware