Sora-Ref

The latest text-to-video model from OpenAI, capable of generating cinematic-quality motion with realistic physics, natural scene continuity, and synchronized sound.
It supports prompts to define scenes, voices and dialogues. Use an image for tighter control Add a reference image (photo, digital art, or AI-made) to lock in character look, wardrobe, set details, and overall style. The model treats that image as the first-frame anchor; your text prompt tells it what happens next. Rules Content must be suitable for under-18 audiences (an opt-out may come later). No copyrighted characters or copyrighted music, No real people, including public figures, Input images with human faces are currently rejected. Make sure your prompts, reference images, and transcripts follow these rules to avoid failures.