NVIDIA

FLUX 3 Image Klein NIM

Container

NVIDIA

FLUX 3 Image Klein NIM

FLUX 3 Image Klein is a state-of-the-art open-weight image generation and editing model

NVIDIA NIM

FLUX 3 Image Klein Container Overview

Description:

This container houses FLUX 3 Image Klein, a 5.6 billion parameter open weights Black Forest Labs model for text-to-image generation and image editing. FLUX 3 Image Klein takes a text prompt and up to 10 reference images and returns one image. Text-to-image generation, single-reference editing and multi-reference composition run through the same model. The model supports bounding boxes in the prompt to place, recolor, move, replace or remove elements, as well as text rendering within generated images.

The container components are ready for non-commercial use. For commercial uses, see Black Forest Labs commercial licensing.

Third-Party Community Consideration:

The models embedded in the container are not owned or developed by NVIDIA. These models have been developed and built to a third-party’s requirements for this application and use case; see link to:

License/Terms of Use:

GOVERNING TERMS: The NIM container is governed by the NVIDIA Software License Agreement and the Product-Specific Terms for NVIDIA AI Products.

The Flux 3 Image Klein model and Flux 3 Image Klein base model are governed by the FLUX Kommunity License v.1.0. Use of the Cosmos Guardrail model is governed by NVIDIA Open Model License Agreement. Use of Cosmos-1.0-Guardrail is governed by the NVIDIA Open Model License Agreement. Additional Information for Cosmos-1.0-Guardrail: Llama 2 Community License Agreement; built with Llama 2.

You are responsible for ensuring that your use of NVIDIA provided models complies with all applicable laws.

Deployment Geography:

Global

Release Date:

build.nvidia.com October 15, 2026 via https://build.nvidia.com/black-forest-labs/flux-3-image-klein
HuggingFace October 15, 2026 via https://huggingface.co/black-forest-labs/flux-3-image-klein
HuggingFace October 15, 2026 via https://huggingface.co/black-forest-labs/flux-3-image-klein-base

FLUX 3 Image Klein:

The FLUX 3 Image Klein Container includes the following models:

Model Name & Link	Use Case	How to Pull the Model
FLUX 3 Image Klein	Distilled checkpoint (16 steps, no guidance) for text-to-image generation, single-reference editing and multi-reference image generation	Automatic
FLUX 3 Image Klein Base	Undistilled base checkpoint (50 steps, with guidance scale) for text-to-image generation and image editing; intended for fine-tuning and LoRA training	Automatic

Deployment Details:

Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA’s hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions.

References

Container Version(s):

nvcr.io/nim/black-forest-labs/flux-3-image-klein:latest

Key Considerations:

The models embedded in this container can generate synthetic images and may produce content that is inaccurate, offensive, or otherwise inappropriate. Users should implement robust safety guardrails — including content filtering, abuse monitoring, and access controls— to reduce the risk of harmful outputs. Users are responsible for ensuring that their use of the model complies with all applicable laws and regulations, and for regularly reviewing and updating their guardrails as risks evolve.

For more information about the implementation of Cosmos pre and post guardrails to improve model safety, please see the Cosmos-1.0 Guardrail Model.

For more information about Black Forest Labs' pre-training and post-training mitigations to improve model safety, please visit the Responsible AI Development section at this link and the Capable, Open, and Safe: Combating AI Misuse blog post.

Security Common Vulnerabilities and Exposures (CVEs)

Please review the Security Scanning tab on NGC to view the latest security scan results. For certain open-source vulnerabilities listed in the scan results, NVIDIA provides a response in the form of a Vulnerability Exploitability eXchange (VEX) document. The VEX information can be reviewed and downloaded from the Security Scanning tab.

Ethical Considerations:

NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal developer team to ensure these software components meet requirements for the relevant industry and use case and address unforeseen product misuse.

Please make sure you have proper rights and permissions for all input image and video content; if image or video includes people, personal health information, or intellectual property, the image or video generated will not blur or maintain proportions of image subjects included.

Users are responsible for model inputs and outputs. Users are responsible for ensuring safe integration of this model, including implementing guardrails as well as other safety mechanisms, prior to deployment.

Please report model quality, risk, security vulnerabilities or NVIDIA AI Concerns here.

Get Help

Getting started with the NIM

Deploying and integrating the NIM is straightforward thanks to our industry standard APIs. Visit the Visual Generative AI NIM page for release documentation, deployment guides and more.