DEVOURED
Black Forest Labs Launches FLUX 3 Capable of Generating Images and 20-second Video with Audio
Black Forest Labs has released FLUX 3, a video generation model capable of 20-second clips with native audio, currently in limited, invite-only release.
What: The new FLUX 3 model supports multi-shot continuity and audio integration, while a derivative model, FLUX-mimic, is being positioned for robotic manipulation tasks.
Why it matters: The entry of Black Forest Labs into the video generation space increases competition for OpenAI's Sora and Runway's Gen-3, with a notable expansion toward physical-world robotics integration.
Original article
Black Forest Labs unveiled FLUX 3, its first public video generation model. Early access requires approval, and the company has not yet disclosed pricing, service-level commitments, or full benchmark methodology. The video tier generates up to 20-second clips with native audio and multi-shot continuity. A related model, FLUX-mimic, extends the same architecture toward robotic manipulation tasks.
Explore all 42 articles in today's digest
Fresh dev news, AI-digested daily. Never miss a trend at devoured.fyi