Black Forest Labs FLUX 3 at a glance
FLUX 3 is trained jointly on images, video, and audio; FLUX 3 Video entered early access first, with image, action, and open-weight versions planned in stages.
What changed with Black Forest Labs FLUX 3
Black Forest Labs announced FLUX 3 on July 23, 2026, describing it as a multimodal foundation model that learns jointly from images, video, and audio in one architecture. It can generate images, video with audio, and mixed outputs from text prompts or image and video references, with clips of up to 20 seconds in a single generation.
The rollout is staged. FLUX 3 Video was the first product in early access, image early access was set to follow in the following weeks, and API and private-weight access are planned for video and image. An action-prediction model built with mimic robotics goes to selected partners, and an open-weight FLUX 3 Dev is planned without a date. BFL says FLUX 3 Video was preferred over Grok Imagine Video in up to 69% of early comparisons.
Where to compare Black Forest Labs FLUX 3
Independent leaderboards and official resources for comparing this model yourself. Rankings change often; each site shows its own current data.
Leaderboards
General leaderboards
Official resources
Why Black Forest Labs FLUX 3 matters for businesses
For marketing teams and agencies, FLUX 3 points toward one model family covering stills and short video with sound. The post gives no pricing or license terms for FLUX 3 itself, so commercial use should be checked as each product leaves early access.
Sources for this story
- FLUX 3 (opens in a new tab)Official
Black Forest Labs · bfl.ai
Last verified: . IA Compa summarizes public announcements for business readers. We are not affiliated with the companies mentioned. Always confirm details, pricing, and availability with the official source.
- #image-generation
- #video-generation
- #black-forest-labs
- #flux