Ray3 Modify introduces a next-generation hybrid AI workflow for acting and performance, allowing brands and studios to shape scenes with greater control, continuity and creative intent.
Luma AI has introduced Ray3 Modify, a new AI-driven video workflow designed to integrate real-life actor performances directly into advanced generative video production, marking a significant step toward more controllable, film-ready AI visuals. Available now on the company’s Dream Machine platform, Ray3 Modify enables creative teams to enhance and transform recorded performances while preserving the timing, movement and emotional intent of the original acting.
The launch addresses one of the long-standing challenges of AI-generated video: maintaining believable and consistent human performance during scene edits and visual transformations. By conditioning AI generation on live-action input footage, Ray3 Modify allows brands, filmmakers and advertisers to work with real actors while using AI to modify environments, styles and cinematic elements without losing performance authenticity.
Unlike earlier AI video systems that rely heavily on text prompts and approximation, Ray3 Modify places the human performer, camera movement and physical staging at the center of creative direction. The system follows real-world motion, framing, pacing and emotional delivery, reducing guesswork and enabling creators to shape scenes with far greater precision and predictability.
The workflow supports production scenarios where continuity and repeatability are critical, allowing original performances to remain intact while visual aspects such as locations, costumes, lighting and overall aesthetic can be reimagined. This hybrid approach opens new possibilities for film, television, advertising and visual effects pipelines that blend live-action capture with AI-driven transformation.
Amit Jain, CEO and co-founder of Luma AI, added: “Generative video models are incredibly expressive but also hard to control. Today, we are excited to introduce Ray3 Modify that blends the real-world with the expressivity of AI while giving full control to creatives. This means creative teams can capture performances with a camera and then immediately modify it to be in any location imaginable, change costumes, or even go back and reshoot the scene with AI, without recreating the physical shoot.”
Ray3 Modify introduces several new capabilities aimed at professional production workflows. These include start and end frame keyframe controls to guide transitions and maintain spatial continuity, character reference tools that lock identity and appearance across shots, and enhanced performance preservation that keeps motion, eye lines and emotional delivery intact. An upgraded model architecture further improves consistency in motion, composition and scene continuity.
Together, these advances position Ray3 Modify as a next-generation AI video tool built for hybrid production, where creative authority begins with human performance and AI acts as an extension rather than a replacement.