Black Forest Labs has officially launched FLUX 3, a video generation model built around a unified architecture jointly trained for images, video, and audio. It can generate up to 20 seconds of native 1080p video with synchronized native audio, and supports text-to-video, image-to-video, video-to-video, continuation with video and audio inputs, keyframe-to-video, multilingual dialogue, and multi-shot sequencing. The company reports benchmark scores of 1,135 for text-to-video and 1,051 for image-to-video, claiming advantages over models including Seedance 2.0 and Minimax H3. Pricing is based on output duration.
No heat snapshots are available in the last 24 hours.