- Luma Labs has launched the new Ray 2 AI video generator
- Ray 2 converts text prompts into high-quality 5-10 second videos
- Ray 2 is available through the Dream Machine platform
Luma Labs has debuted a powerful new AI model for generating videos on its Dream Machine platform called Ray 2. The new model can produce a variety of realistic video clips of up to 10 seconds, from a recreation of a bee pollinating flowers to more ideas. surreal like the typographic anthropomorphic banana seen above.
The beauty of Ray 2 is not only its ability to depict these wild settings, but also to do so with movement and physics that look surprisingly natural. Unlike previous video generation tools, which often struggled to produce anything faster than a leisurely walk, you can see people booking it in one go. Ray 2 is able to achieve this level of output due in part to Luma training it with ten times the computing power of its predecessor, Ray 1. That means more realistic characters, faster rendering, smoother movements, and far fewer glitches.
Ray 2 is available through Luma’s Dream Machine platform, which offers free and paid subscription tiers. The free plan allows users to try 720p resolutions, while the paid plans unlock higher quality 1080p images and unlimited use if you’re willing to spend $66.49 a month.
Look
AI Video Sprint
Surrealism: “a photorealistic anthropomorphic banana tree doing taxes” pic.twitter.com/OQCFaSRRWEJanuary 15, 2025
Luma plans to expand Ray 2’s capabilities with image-to-video, video-to-video, and editing tools. That could mean allowing you to turn a vacation photo into a short video or remix a home movie into something cinematic.
The company also hosts the Ray 2 Awards, offering creators the chance to win up to $7,000 in prizes. There’s a $5,000 prize for the most viewed Ray 2 video on social media and a $3,000 raffle for anyone who shares their content and engages with Luma’s promotional posts. If nothing else, it’s a good excuse to finally make his “sloths competing in a high-stakes basketball game” idea come true.
However, Ray 2’s limits mean it won’t eliminate any competition. The time limit makes it less capable than OpenAI’s Sora model in some ways. Sora focuses on creating longer, coherent video narratives. Then there’s Runway’s Gen-2, which gives users tools to modify lighting, camera angles, and more, and Pika, which regularly releases new features like the image-to-video conversion capability that Luma is still developing.
Still, the Ray 2 has its charm and feels like a streamlined alternative for those who prioritize speed and ease of use. The real importance of Ray 2 lies in how it helps lower the barrier to entry for anyone wanting to make an AI video. Even if that’s something as strange as a banana writing a note.
You may also like…