New Delhi: AI Startup Luma AI has launched the latest Ray3 model, which is much powerful to convert text to a video AI model with built-in reasoning, designed for high-quality cinematic visual production for professionals. Luma has also released a partnership with Adobe to integrate the latest model into the Adobe AI-enabled Firefly application, the company’s all-in-one software for creative work. Ray3 is a step ahead in building intelligence for the innovative work by the co-founder of Luma AI.
This is Ray3. The world’s first reasoning video model, and the first to generate studio-grade HDR. Now with an all-new Draft Mode for rapid iteration in creative workflows, and state of the art physics and consistency. Available now for free in Dream Machine. pic.twitter.com/qm29hkDA14
— Luma AI (@LumaLabsAI) September 18, 2025
Creative work is one of the most intellectually challenging things humans do, yet until now, much of the AI available to creatives has lagged far behind what’s possible in coding and analysis with the language models. Ray3’s flagship capability is chain of thought reasoning, which allows it to think through scene descriptions and follow the instructions from the creative professionals. Generative video models on the market have been more like slot machines, exhibiting much power but little intelligence.
Ray3 can evaluate its own outputs and refine them to better preserve the artistic vision of the users; it can plan out complex scenes and judge whether its output makes sense before presenting it. The model works in a manner similar to animators and filmmakers, sketching out a storyboard before generating the final product. During the drafting process, users can collaborate with the model to provide more precise instructions, such as annotating portions of the video. The model can then follow along with some of the complex ideas in the video generatively, with the multi-step ideals. It also understands visual annotations, such as the lines drawn on video stills during drafting, enabling it to follow the user’s instructions more precisely. This AI model is helpful for those video editors who want a creative touch in their videos. So they can check it out for their upcoming generative creative video for the content.
