black-forest-labs / flux-3-action-base

FLUX 3 Action Base

FLUX 3 Action is an open weights 7B world action model. It takes camera frames, the robot's state and a text instruction, and returns the next chunk of actions, denoised together with the next video frames. This repository is part of the FLUX 3 Action collection .

For more information, read the documentation .

Action base weights for embodiment adaptation, plus the shared frozen encoders used by the SO-101 and DROID policies. This is an adaptation component, not a complete robot policy. See License for usage terms.

The base has 457 tensors, with video and text streams, a shared action trunk, and ee50/gaming action heads. New embodiments require their own action heads. The text encoder is an unmodified copy of Qwen/Qwen3-VL-4B-Instruct; its model card and license designation are preserved in text_encoder/README.md .

Load ready-to-use robot policies from SO-101 or DROID . Their configurations reference these shared encoders automatically.

Download just the adaptation base with:

hf download black-forest-labs/flux-3-action-base flux-3-action-base.safetensors

To train heads for a new robot, simulator or game, follow Fine-tune .

Out-of-scope use

FLUX 3 Action outputs joint targets. Nothing in the model bounds joint velocity, force or workspace; the application must enforce those limits and keep a hardware stop within reach. Validate on a simulator or with the arm's safety limits engaged before running near people.

The model and its derivatives may not be used:

• In any way that violates applicable law.
• To control a machine in a way that endangers people, without human oversight and a means to stop it.
• For fully automated decision making or high risk applications that adversely impact an individual's legal rights or otherwise create or modify a binding, enforceable obligation.
• To harass, abuse, threaten, stalk, or bully individuals or groups of individuals.
• For the purpose of exploiting, harming or attempting to exploit or harm minors in any way.

Nothing contained in this model card should be interpreted as or deemed a restriction or modification to the license the model is released under.

Responsible AI development

Black Forest Labs is committed to responsible model development and deployment. FLUX 3 Action outputs motor commands and, on request, predicted camera frames of the scene it is acting in. For information about our mitigations, evaluation processes and policies, see Capable, Open, and Safe: Combating AI Misuse . To report safety concerns, contact [email protected] .

License

This model falls under the FLUX Kommunity License v.1.0 . The text encoder in flux-3-action-base is an unmodified copy of Qwen3-VL-4B-Instruct under Apache-2.0. The code in flux-action has its own license.

Trademarks and IP

This project may contain trademarks or logos for projects, products, or services. Use of Black Forest Labs and FLUX trademarks or logos in modified versions of this project must not cause confusion or imply sponsorship or endorsement. Any use of third-party trademarks, intellectual property or logos are subject to those third-party's policies.