FLUX 3 Action

FLUX 3 Action

Black Forest Labs
Genie 4

Genie 4

Google
+
+

Related Products

  • LTX
    182 Ratings
    Visit Website
  • Adobe Firefly
    25,051 Ratings
    Visit Website
  • SAP S/4HANA Cloud Public Edition
    4,608 Ratings
    Visit Website
  • Jama Connect
    416 Ratings
    Visit Website
  • Grafana Cloud
    861 Ratings
    Visit Website
  • Screencapt
    140 Ratings
    Visit Website
  • Shoplogix Smart Factory Platform
    19 Ratings
    Visit Website
  • D&B Finance Analytics
    802 Ratings
    Visit Website
  • Haast
    5 Ratings
    Visit Website
  • UptimeRobot
    880 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

Genie 4 is a generative AI world model developed by Google DeepMind that creates realistic, interactive virtual environments in real time. The model generates explorable worlds with dynamic visuals, native audio, physical interactions, and responsive human characters. Users can navigate generated environments using keyboard controls and modify scenes through natural language instructions, including changing weather conditions, moving cameras, and introducing objects. Its physics simulation capabilities model phenomena such as aerodynamics, collisions, and natural human movement. Genie 4 integrates with Google's Gemini models to support complex reasoning, multistep event simulation, and interactive environments that respond coherently to user actions. The model is available as a limited research preview for trusted testers, with planned access through Project Genie, Google AI Studio, and the Gemini API.

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 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

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

AI researchers, robotics engineers, autonomous agent developers, game developers, filmmakers, visual effects artists, simulation engineers, educators, creative technologists, and organizations seeking real-time AI-generated environments, interactive world simulation, physics modeling, and virtual training experiences

Support

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

Support

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

API

Offers API Supported

API

Offers API Supported

Screenshots and Videos

Screenshots and Videos

Pricing

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

Pricing

No information available.
Free Version Not 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 Not Supported
In Person Not Supported

Company Information

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

Company Information

Google
Founded: 1998
United States
deepmind.google/

Alternatives

Odyssey-3

Odyssey-3

Odyssey

Alternatives

Gemini Omni

Gemini Omni

Google
GWM-1

GWM-1

Runway AI
Veo 3

Veo 3

Google
Starchild-1

Starchild-1

Odyssey
Genie 3

Genie 3

Google DeepMind
Project Genie

Project Genie

Google DeepMind
Gemini Robotics-ER 1.6

Gemini Robotics-ER 1.6

Google DeepMind

Categories

AI Models Supported
AI World Models Supported

Categories

AI Models Supported
AI World Models Supported

Integrations

Gemini Not Supported
Gemini Enterprise Not Supported
Google AI Studio Not Supported
Project Genie Not Supported

Integrations

Gemini Supported
Gemini Enterprise Supported
Google AI Studio Supported
Project Genie Supported
Claim FLUX 3 Action and update features and information
Claim FLUX 3 Action and update features and information
Claim Genie 4 and update features and information
Claim Genie 4 and update features and information