black-forest-labs/flux-3-video is Black Forest Labs' advanced multimodal video generation model, designed to create high-quality video with native synchronized audio. It can generate videos from text prompts, animate images, and transform existing video content while maintaining strong visual consistency, realistic motion, and natural interactions between objects and characters. FLUX 3 Video is built around a unified multimodal architecture that jointly understands images, video, and audio, allowing it to generate video and sound together rather than treating audio as a separate post-production step. It can produce clips of up to 20 seconds in a single generation and is particularly strong at facial expressions, physical interactions, and connecting sounds with events in the scene.