Black Forest Labs Launches FLUX 3 Video with Native Audio and 1080p

bfl_ai · x · 2026-08-05

Black Forest Labs has officially released the FLUX 3 Video model. The model supports text-to-video, image-to-video (with start, end, or multiple keyframes), video continuation, and multilingual dialogue. It can generate native 1080p video up to 20 seconds in a single generation, complete with native audio (including effects, ambience, and accurate lipsync).

To reduce creative costs, the model introduces a Draft mode, allowing users to quickly preview ideas at a fraction of the cost before rendering at full quality. The API is now available, with 2K, 4K resolutions, and open weights coming soon.

Related event: Black Forest Labs Launches FLUX 3 Multimodal Model(11 posts)→

Original post →

More from Multimodal

Multimodal channel →