Ray 3.2

Ray 3.2 is Luma AI's latest video generation model that turns text descriptions, images, or source footage into cinematic clips. It runs entirely in the browser, requiring no downloads or local GPU resources. The product supports four workflows—text‑to‑video, image‑to‑video, video edit, and video reframing—so users can generate new footage, animate still images, restyle existing clips, or change aspect ratios while preserving motion, structure, and timing. Key capabilities include frame‑level control with up to 16 keyframes per clip, native 1080p HDR output, 16‑bit EXR export, and support for clips up to 20 seconds. Advanced features cover facial performance transfer, motion transfer, environment swapping, relighting, and campaign localization. Ray 3.2 is aimed at creators, marketers, agencies, and studios that need professional‑grade video without expensive production, and it offers full API access for integration into existing pipelines.