FLUX 3 Action

FLUX 3 Action

Black Forest Labs
Gemini Robotics

Gemini Robotics

Google DeepMind
+
+

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

Gemini Robotics brings Gemini’s capacity for multimodal reasoning and world understanding into the physical world, allowing robots of any shape and size to perform a wide range of real-world tasks. Built on Gemini 2.0, it augments advanced vision-language-action models with the ability to reason about physical spaces, generalize to novel situations, including unseen objects, diverse instructions, and new environments, and understand and respond to everyday conversational commands while adapting to sudden changes in instructions or surroundings without further input. Its dexterity module enables complex tasks requiring fine motor skills and precise manipulation, such as folding origami, packing lunch boxes, or preparing salads, and it supports multiple embodiments, from bi-arm platforms like ALOHA 2 to humanoid robots such as Apptronik’s Apollo. It is optimized for local execution and has an SDK for seamless adaptation to new tasks and environments.

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

Robotics researchers and developers wanting a solution to enable diverse robots to perceive, reason about, and interact with real-world environments

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 Not 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 Not 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 DeepMind
Founded: 2010
United Kingdom
deepmind.google/models/gemini-robotics/

Alternatives

Gemini Robotics-ER 1.6

Gemini Robotics-ER 1.6

Google DeepMind

Alternatives

Gemini Robotics 2

Gemini Robotics 2

Google DeepMind
Gemini Robotics 2

Gemini Robotics 2

Google DeepMind
Gemini Robotics-ER 1.6

Gemini Robotics-ER 1.6

Google DeepMind
FLUX 3

FLUX 3

Black Forest Labs
Gemini Robotics

Gemini Robotics

Google DeepMind
Starchild-1

Starchild-1

Odyssey

Categories

AI Models Supported

Categories

AI Models Supported

Integrations

AlphaFold Not Supported
Gemini Not Supported
Gemini Enterprise Not Supported
Gemini Robotics-ER 1.6 Not Supported
Gemma Not Supported
Google AI Studio Not Supported
Google Cloud Platform Not Supported
Imagen Not Supported
Lyria Not Supported
SynthID Not Supported
Veo 2 Not Supported
Veo 3 Not Supported
Veo 3.1 Not Supported
WeatherNext Not Supported

Integrations

AlphaFold Supported
Gemini Supported
Gemini Enterprise Supported
Gemini Robotics-ER 1.6 Supported
Gemma Supported
Google AI Studio Supported
Google Cloud Platform Supported
Imagen Supported
Lyria Supported
SynthID Supported
Veo 2 Supported
Veo 3 Supported
Veo 3.1 Supported
WeatherNext Supported
Claim FLUX 3 Action and update features and information
Claim FLUX 3 Action and update features and information
Claim Gemini Robotics and update features and information
Claim Gemini Robotics and update features and information