ICYMI: Black Forest Labs opens FLUX 3 Video early access

Black Forest Labs has opened early access to FLUX 3 Video, the first released component of its FLUX 3 multimodal foundation model trained jointly on images, video, and audio.

FLUX 3 Video can generate up to 20-second videos with native audio, continue scenes and dialogue, and extend clips into longer sequences.

The company said benchmark tests showed strong preferences versus several competing video models.

Broader access is planned later through APIs, private weights, and an open-weight dev version.

The launch points to progress toward unified AI systems that can create and understand multiple media types in one model.