Black Forest Labs Unveils FLUX 3, a Unified Image, Video, Audio and Robotics Model
AI video model releases
Black Forest Labs Unveils FLUX 3, a Unified Image, Video, Audio and Robotics Model
Black Forest Labs launches FLUX 3, a single multimodal architecture trained jointly on images, video and audio, built on the company's Self-Flow method rather than combining separate models
FLUX 3 Video enters early access first, generating up to 20-second clips with native audio in one pass, supporting text-to-video, image animation, video transformation and footage continuation
In preliminary 720p/10-second tests, FLUX 3 beat Luma Ray 3.2 in 93% of comparisons and Runway Gen-4.5 in 77%, with 52% wins against both Seedance 2.0 and Gemini Omni Flash
Rollout splits into four product lines: FLUX 3 Video, FLUX 3 Image (early access in coming weeks), FLUX 3 Action/FLUX-mimic for robotics, and FLUX 3 Dev as an open-weight multimodal backbone
Mimic Robotics is an early partner building FLUX-mimic, adapting the video backbone's motion understanding for dexterous robotic manipulation and production deployment
cho.sh