SSyncDev

FLUX 3 Action

SyncDev model directory · Profile updated Nov 18, 2026

Compare with another model

FLUX 3 Action is Black Forest Labs' open 7B world action model for robots, predicting action chunks and future video from cameras, state and text.

Key specifications

Specification score
9.7
License
FLUX Kommunity License v1.0

The specification score summarizes recorded features and limits. It is not a benchmark result.

Pricing conditions: Open weights; no per-token price is published. Your cost is the GPU time you run it on.

Inputs and outputs

Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.

Accepts

  • Image input
  • Text input

Produces

  • Text output

Capabilities

VisionOpen weights

What is FLUX 3 Action?

Black Forest Labs made its name on image generation. FLUX 3 Action takes the same backbone into robotics. It is a 7B open-weights world action model: given camera frames, the robot's current state and a text instruction, it predicts the next chunk of actions and, jointly, what the cameras should see next. The current API returns only the actions.

Predicting the visual outcome is the point. A model that has to imagine the result of a grasp is pushed toward physically sensible plans.

Embodiments out of the box

Embodiment Cameras Action Chunk
DROID (Franka arm) 3, composited to 736 × 544 7 joints + gripper 32 steps, about 2 s at 15 Hz
SO-101 (LeRobot) 2, side by side at 512 × 256 6 joint commands 42 steps at 30 Hz
Video game 1 frame at 256 × 256 3–4 values in [-1, 1] 32 steps
Drone (Isaac Sim) 1 onboard frame forward, lateral, up, yaw —

DROID and SO-101 have ready checkpoints. Other robots need their own action heads; the base repository is an adaptation component, not a complete policy. Black Forest Labs' fine-tuning example taught an SO-101 a pick-and-place skill from about 200 demonstrations with LeRobot and a LoRA.

Files and licence

The base ships the action model, a shared video VAE, and an unmodified Qwen3-VL-4B-Instruct as text encoder (Apache-2.0). The model itself is under the FLUX Kommunity License v1.0, and the Hugging Face repository is gated.

On the benchmark claim

Launch coverage on 23 September 2026 put it at 42.92% on NVIDIA's RoboLab-120, about 6.1 points ahead of Cosmos3-Nano-Policy. The model card reports no benchmarks at all, and coverage disagrees on the size of the NVIDIA comparison model. Treat the ranking as indicative and run your own tasks.

Safety first

Outputs are joint targets with no limits on velocity, force or workspace. Your controller must enforce them. Validate in simulation, then on hardware with safety limits engaged and a physical stop within reach. Record twenty demonstrations of one task, fine-tune, and measure success over fifty trials before adding a second task.

More vision-action and multimodal models are under multimodal; for an open alternative trained only on public data, compare REKI-2B.

How to evaluate FLUX 3 Action

Compare the model on the work you need to complete.

Tasks and inputs

FLUX 3 Action is listed for Image-to-video, Multimodal. It accepts image, text and produces text. Use the publisher’s input format and preprocessing for your chosen deployment.

Capacity and cost

Measure a completed task using the prompts, documents and tools your application will use. Include reasoning and retries in the result.

Choosing a deployment

The weights are downloadable under FLUX Kommunity License v1.0. Check runtime support and size the complete model and working context for your expected concurrency.

Frequently asked questions

The next chunk of robot actions together with future video latents, from camera frames, robot state and a text instruction.

These records share a directory category. Check the source card, output type and deployment requirements before treating a model as a replacement.

NVIDIA

Alpamayo 2 Edge

Alpamayo 2 Edge is NVIDIA's open 2B-class driving VLA that outputs trajectories with causal explanations, sized for DRIVE AGX Thor in-vehicle use.

— context

shanghai-ai-lab

Sage-SciPerception

Sage-SciPerception is Shanghai AI Lab's set of projectors feeding crystals, spectra, biological sequences and biosignals into a language model's input.

— context

inclusionAI

Ling 3.2 Flash

Ling 3.2 Flash is inclusionAI's 560B-A25B multimodal MoE with a 1M-token window, built for visual agents, 3D tasks and medical image reasoning.

1M context

Swiss AI

Apertus 1.5 8B

Apertus 1.5 8B is the Swiss AI Initiative's open multilingual model, now taking text, images and audio with a 262K-token context window.

262.14K context

kyutai

REKI-2B

REKI-2B is Kyutai's open 2.4B robot vision-language-action model with cheap register-token memory, pretrained only on public data.

— context