FLUX by Black Forest Labs

Black Forest Labs is the AI lab behind the FLUX image and video models. Its site is where you try the newest models, get API access and download open weights.

FLUX 3

As of October 2026 the current generation is FLUX 3, presented as one multimodal model family:

• Image: realistic and stylised images with highly accurate text rendering and good handling of complex prompts. A smaller FLUX 3 Image Klein variant is also listed.
• Video: clips of up to 20 seconds in a single generation, started from text, an image or keyframes, with optional generated audio (multilingual speech, effects and ambience) and several shots in one take.
• Action: FLUX 3 Action, an open-weights 7B "world action model" for robotics that predicts physical outcomes and robot control actions.
• FLUX Tools for editing and control.

Three ways to use it

• Playground: try the models in your browser without writing code.
• API: an API built for production workloads, with docs and a dashboard.
• Open weights: some models can be downloaded from Hugging Face and GitHub and run on your own hardware, under BFL's own licences (including non-commercial terms); commercial self-hosting needs a licence.

FLUX models also appear inside other products, such as Adobe Firefly's partner models.

Who it's for

Developers building image or video features into their products, and creators who want direct access to FLUX instead of a third-party wrapper.

Related on SleekNav

Other image generators: Midjourney and Leonardo.ai.