Luma AI

[Luma](https://lumalabs.ai/)

- [DreamMachine](https://lumalabs.ai/dream-machine)
- [Ray2](https://lumalabs.ai/ray2)
- [Photon](https://lumalabs.ai/photon)
- [API](https://lumalabs.ai/dream-machine/api)
- [Pricing](https://lumalabs.ai/dream-machine/pricing)
- [Genie](https://lumalabs.ai/genie)
- [Capture](https://lumalabs.ai/interactive-scenes)
- [JoinUs](https://lumalabs.ai/join)
- [Learninghub](https://lumalabs.ai/learning-hub)
- [innerCircle](https://lumalabs.ai/dream-machine/inner-circle)
- [Discord](https://discord.g/lumaai)
- [Twitter](https://x.com/LumaLabsAI)
- [Mediakit](https://www.dropbox.com/scl/fo/xgvmuzp0b8kotl45k8f7t/ADRsEghq6ArcRtlSoz_AJ2Y?rlkey=756ogtx0r3rg7kgvzfagqv6o9&e=1&st=jxx13zfe&dl=0)
- [ContactUs](mailto:[email protected])
- [TermsofService](https://lumalabs.ai/legal/tos)
- [PrivacyPolicy](https://lumalabs.ai/legal/privacy)

Luma

### IntroducingRay2

Ray2 is a large–scale video generative model capable of creating realistic visuals with natural, coherent motion. It has strong understanding of text instructions and can take image and video as input

### IntroducingRay2Flash

Free users can now generate with Ray2’s Text-to-Video and Image-to-Video models at a third of the price and 3x faster. High-quality, efficient, and more accessible than ever

### ImagetoVideoforRay2

Built on the vast scale and capabilities of Ray2, create visually stunning, high-quality results from any image in seconds

### Keyframe,extendandloopforRay2Keyframe,extendandloopforRay2

Create your visual story with precise frame-by-frame control, seamless transitions, spatial exploration and long-form video durations using Ray 2 Text-to-Video and Image-to-Video models in Dream Machine

### \_\_

.

.

..

[TryNowinDreamMachine](https://dream-machine.lumalabs.ai/)

Luma

## Luma's mission is to build multimodal general intelligence that can generate, understand, and operate in the   physical world

[Joinus](https://lumalabs.ai/join)

01

AI for the next billion people will not look like LLMs. Computers won’t be point and click. Tomorrow’s systems will be creative, immersive, and multimodally interactive.

**Text alone is not enough to get there.** The current industry approach of scaling LLMs on limited text data has hit a wall. At Luma we are doing foundational research and building systems that can train efficiently on rich multimodal data. This is the path to useful general intelligence.

**We are training world models that jointly learn from video, audio, and language — similar to how the human brain learns.** This will enable models to see, hear and reason about the world so they can effectively collaborate with us, help us communicate better, entertain us, and one day, operate alongside us in the real world.

We are a small stellar team of researchers, engineers, and product thinkers dedicated to this singular mission. If that's you, we offer an opportunity to do your life's work and solve one of the most important problems of our time in a colle…