Luma AI has released Ray2, its latest AI video generation model, offering improved motion quality and physics simulation in generated videos. According to reporting by Carl Franzen, the new model was trained with ten times more computing power than its predecessor. The San Francisco-based company’s CEO Amit Jain announced that Ray2 delivers faster and more natural coherent motion, making video creation more accessible to users. The model is available through Luma’s Dream Machine platform and mobile apps for subscribers, with plans starting at $6.99 per month. Currently, Ray2 allows users to create 5-10 second video clips from text descriptions, with image-to-video and video-to-video capabilities planned for future updates. Early users report impressive results, particularly in creating fluid, lifelike movements, though some complex prompts can still produce glitchy results. The company has launched the Ray2 Awards competition, offering prizes up to $7,000 for creators using the new model. Luma’s release comes amid increasing competition in the AI video generation space, with recent launches from companies like Runway, OpenAI, and Google.