FLUX 3 Action

FLUX 3 Action

Black Forest Labs
+
+

Related Products

  • Adobe Firefly
    25,030 Ratings
    Visit Website
  • SAP S/4HANA Cloud Public Edition
    4,559 Ratings
    Visit Website
  • LTX
    182 Ratings
    Visit Website
  • Screencapt
    140 Ratings
    Visit Website
  • Grafana Cloud
    860 Ratings
    Visit Website
  • Shoplogix Smart Factory Platform
    19 Ratings
    Visit Website
  • Jama Connect
    387 Ratings
    Visit Website
  • Haast
    4 Ratings
    Visit Website
  • JetBrains Junie
    12 Ratings
    Visit Website
  • UptimeRobot
    852 Ratings
    Visit Website

About

FLUX 3 Action is an open-weight 7B world-action model designed for action prediction in robotics and other latency-sensitive visual environments. Derived from the multimodal FLUX 3 backbone, it was pretrained on large-scale image, video, and audio data with a strong emphasis on video, then adapted through joint video-action training and fine-tuning for specific embodiments and action spaces. Given an instruction, camera observations, and robot joint positions, the model predicts motor commands together with their expected visual outcomes, allowing a robot to execute actions, observe the environment again, and continuously replan. Unlike approaches that separate visual prediction from control, FLUX 3 Action jointly models future video and actions, transferring world understanding learned from broad video pretraining into robot control. Its single-step 7B checkpoint reaches a 38.3% success rate on RoboLab-120.

About

NVIDIA Cosmos is a developer-first platform of state-of-the-art generative World Foundation Models (WFMs), advanced video tokenizers, guardrails, and an accelerated data processing and curation pipeline designed to supercharge physical AI development. It enables developers working on autonomous vehicles, robotics, and video analytics AI agents to generate photorealistic, physics-aware synthetic video data, trained on an immense dataset including 20 million hours of real-world and simulated video, to rapidly simulate future scenarios, train world models, and fine‑tune custom behaviors. It includes three core WFM types; Cosmos Predict, capable of generating up to 30 seconds of continuous video from multimodal inputs; Cosmos Transfer, which adapts simulations across environments and lighting for versatile domain augmentation; and Cosmos Reason, a vision-language model that applies structured reasoning to interpret spatial-temporal data for planning and decision-making.

Platforms Supported

Windows Not Supported
Mac Not Supported
Linux Not Supported
Cloud Supported
On-Premises Not Supported
iPhone Not Supported
iPad Not Supported
Android Not Supported
Chromebook Not Supported

Platforms Supported

Windows Supported
Mac Not Supported
Linux Supported
Cloud Supported
On-Premises Not Supported
iPhone Not Supported
iPad Not Supported
Android Not Supported
Chromebook Not Supported

Audience

Robotics researchers, AI developers, and embodied-agent teams seeking to predict and execute actions from multimodal observations with a fast, open-weight world-action model

Audience

Robotics and autonomous vehicle developers needing a solution to simulate, train, and fine-tune physical AI systems

Support

Phone Support Not Supported
24/7 Live Support Not Supported
Online Supported

Support

Phone Support Supported
24/7 Live Support Not Supported
Online Supported

API

Offers API Supported

API

Offers API Not Supported

Screenshots and Videos

Screenshots and Videos

Pricing

No information available.
Free Version Not Supported
Free Trial Not Supported

Pricing

Free
Free Version Supported
Free Trial Not Supported

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Training

Documentation Supported
Webinars Not Supported
Live Online Not Supported
In Person Not Supported

Training

Documentation Supported
Webinars Supported
Live Online Supported
In Person Supported

Company Information

Black Forest Labs
Founded: 2024
Germany
bfl.ai/models/flux-3-action

Company Information

NVIDIA
Founded: 1993
United States
www.nvidia.com/en-us/ai/cosmos/

Alternatives

Gemini Robotics-ER 1.6

Gemini Robotics-ER 1.6

Google DeepMind

Alternatives

Genie 3

Genie 3

Google DeepMind
Gemini Robotics 2

Gemini Robotics 2

Google DeepMind
GWM-1

GWM-1

Runway AI
FLUX 3

FLUX 3

Black Forest Labs
Marble

Marble

World Labs
Gemini Robotics

Gemini Robotics

Google DeepMind
Starchild-1

Starchild-1

Odyssey
BIOVIA COSMO-RS

BIOVIA COSMO-RS

Dassault Systèmes

Categories

AI Models Supported

Categories

AI Models Supported
Foundation Models Supported

Integrations

GitHub Not Supported
Hugging Face Not Supported
NVIDIA Isaac Sim Not Supported

Integrations

GitHub Supported
Hugging Face Supported
NVIDIA Isaac Sim Supported
Claim FLUX 3 Action and update features and information
Claim FLUX 3 Action and update features and information
Claim NVIDIA Cosmos and update features and information
Claim NVIDIA Cosmos and update features and information