Black Forest Labs' video generation model in the FLUX 3 family, with native audio and clips up to 20 seconds.
Updated EU status checked Last shown
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
FLUX 3 Video is the video model in Black Forest Labs' FLUX 3 family, which the company describes as a single multimodal model spanning image, video, audio and action prediction. It generates clips of up to 20 seconds in one generation, with native audio, and can start from text, an image, or keyframes. It can produce multiple shots in a single take and is positioned as stylistically diverse beyond cinematic looks.
The pricing page lists two video tiers: FLUX 3 Video, which balances quality, cost and latency, and FLUX 3 Video Draft, aimed at rapid, cost-effective exploration (available only in HD). Related tools include FLUX Video Edit [fast] for targeted video edits and FLUX 3 Upscale in precise and creative variants. A YouTube reviewer who tested it in Runway reported multi-angle scenes and a somewhat AI-looking result; an open-weight variant was said to be planned.
Access is through Black Forest Labs' browser playground and pay-as-you-go API, with no subscription or seat fees. It is also reported to be available in partner platforms such as Leonardo and Runway. Enterprise licensing is offered for larger organizations. Open weights are not confirmed for the video model.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Black Forest Labs video model now widely available in Leonardo, Runway and others, generating clips up to 20 seconds and claiming accurate reality modeling. Creator tested it in Runway with the same prompts; it produced multi-angle scenes and looked more AI-like. An open-weight variant is planned.
Closest neighbours by meaning, not just by category.
Model · Black Forest Labs
Black Forest Labs image model with bounding-box layout control, reference-image input and native 4K output.
Model · Black Forest Labs
7B open-weights world action model from Black Forest Labs that jointly predicts video and actions for robot control.
Model · Black Forest Labs
9B-parameter open-weights image generation and editing model from Black Forest Labs, built for low-latency use.
Model · Black Forest Labs
5.6B-parameter open-weights model from Black Forest Labs for image editing, text-to-image and multi-reference composition.
Model · Hao AI Lab
Open-weight 4-step sparse-distilled version of MiniMax H3 for fast text-to-video-and-audio generation on Blackwell GPUs.
Model · Google
Google DeepMind's video generation model producing clips with natively generated audio, dialogue and sound effects.
