Dream Machine v1
ProprietaryMultimodal
About
Luma's initial text-to-video model supporting image-to-video. Max 120 characters text input, up to 10 seconds duration at 720p.
Capabilities
VisionMultimodalReasoningFunction CallingTool UseJSON ModeCode Execution
Providers(1)
| Provider | Input (per 1M) | Output (per 1M) | Type | |
|---|---|---|---|---|
| Luma API | — | — | Serverless |
Created by
AI: Imagining the world, in motion
San Francisco, California, United States
Founded 2021
Website