WHAT IT IS
Dream Machine is a text-to-video model Luma AI launched in June 2024, usable directly on the web. It accepts text or image input and generates clips of about 5 seconds at 24 frames per second and 1360×768 resolution. On release, its comparatively fast generation and free trial quota drew a large user base. The model does not release its weights.
Why it matters
With a low barrier to trial and a direct web entry, it let ordinary users quickly turn text into short video, making it one of the consumer-facing text-to-video options of 2024.
Key specs
- Resolution
- 1360×768
- Duration
- About 5 seconds
- Frame rate
- 24 fps
- Input
- Text, image
- Open weights
- No
Capabilities
Related concepts
Diffusion Models
Learn a thousand tiny denoising steps, and you can build an image from pure noise
Multimodal Generation
One model that learns to speak, to draw, to move — even to model the 3D world
Training & Inference Infrastructure
Memory decides how large a model you can train, communication how long it takes — raw compute is rarely the bottleneck
Comparable products
Sora
2024Generates coherent video up to about a minute long from a description
Gen-3 Alpha
2024A highly controllable text-to-video model for film and advertising
Kling
2024A short-video model for both text-to-video and image-to-video
Hailuo
2024A short-video model focused on instruction following and camera language
Veo
2024Generates 1080p video clips with coherent shots
Stable Video Diffusion
2023Turns a single still image into a short video with a diffusion model