FLUX.2 Klein 4B for ComfyUI

FLUX.2 Klein 4B for ComfyUI

Repackaged FLUX.2 Klein 4B model files for ComfyUI that turn a text prompt into an image. Includes diffusion models, text encoders and a VAE, with a ready text-to-image workflow.

Made by Comfy-Org on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face.

About

What it is: These are FLUX.2 Klein 4B model files repackaged for ComfyUI, a node-based tool that turns a text prompt into an image. The repository holds two diffusion models, two text encoders and a VAE. The card also lists a ComfyUI workflow that uses them. The original models come from Black Forest Labs.

Who it suits: It suits ComfyUI users who want the FLUX.2 Klein 4B files in the layout ComfyUI expects, without converting anything themselves.

Industry | Who uses it | How they use it | Example
Design and art | Digital artists | Generate images from text prompts in ComfyUI | A written description becomes a picture
Marketing | Content teams | Draft visuals for posts and campaigns | A prompt produces a first image to refine
Software development | Developers who build image pipelines | Use the files as parts of a ComfyUI workflow | The diffusion model, text encoder and VAE load as separate nodes

You can skip it if you do not use ComfyUI, since these files are packaged for it.

Where to use it:

• ComfyUI, on Windows, macOS or Linux
• The ComfyUI text-to-image workflow template for FLUX.2 Klein 4B from Comfy-Org
• Python with the Hugging Face tools, to download the files

Use case | Who | What they get back
Text to image | Artists and designers | An image generated from a text prompt
Trying the base model | ComfyUI users | Output from the base 4B diffusion model
Building workflows | Pipeline developers | Separate model, text encoder and VAE files to wire together

How to set it up: You need ComfyUI and a place for each downloaded file.

• A working ComfyUI install
• Python with the huggingface_hub package
• Disk space for the diffusion models, text encoders and VAE

1. Install the Hugging Face tools with Python.
2. Download the repository files with the second command below.
3. Place each file in the matching folder under ComfyUI/models, as the table below shows.
4. Open the listed workflow in ComfyUI.

pip install -U huggingface_hub
hf download Comfy-Org/Flux-2-Klein-4B

Title: Where each file goes under ComfyUI/models
Folder | File
diffusion_models | flux-2-klein-4b.safetensors
diffusion_models | flux-2-klein-base-4b.safetensors
text_encoders | qwen_3_4b.safetensors
text_encoders | qwen_3_4b_fp4_flux2.safetensors
vae | flux2-vae.safetensors

How to use it: The card gives no command. Open the listed workflow in ComfyUI, type a description of the image you want, and run it.

Tool | What it does
Klein 4B text-to-image workflow | Comfy-Org template that wires the model files together for text-to-image

Example: You place the files, open the Klein 4B text-to-image workflow, type a short description of a scene, and run it. ComfyUI returns an image generated from that text.

For newcomers and experts: Think of it as an image generator that plugs into ComfyUI. A first small try is to put the files in their folders, open the workflow and run a short prompt.

The repository splits the model into parts that ComfyUI loads separately. Two diffusion models sit beside two Qwen 3 4B text encoders, one of them an fp4 build for FLUX.2, and a single VAE. A regular and a base model are both included, so you can choose the one you want to run.

Place the files in the ComfyUI models folders
Open the Klein 4B text-to-image workflow
Write a text prompt
Run the workflow
Get a generated image

Good to know:

• Repackaged files: they are the original FLUX.2 Klein 4B weights arranged for ComfyUI, and the original repositories belong to Black Forest Labs
• Folders matter: each file belongs in its own subfolder under ComfyUI/models
• One workflow listed: the card shows a single template, for text to image
• License: Apache 2.0
• Cost to run: none named
• Data it reaches: the files you download and the prompts you run in ComfyUI
• Not for: use outside ComfyUI, since the files are repackaged for it

On Hugging Face, 13 November 2026

• Task: text to image
• Library: diffusion-single-file
• Downloads in the last 30 days: 1,291,519
• Likes: 125
• License: apache-2.0
• Based on: black-forest-labs/FLUX.2-klein-4B
• Tags: diffusion-single-file, comfyui, text-to-image

Links

• Model: https://huggingface.co/Comfy-Org/Flux-2-Klein-4B
• Files: https://huggingface.co/Comfy-Org/Flux-2-Klein-4B/tree/main

Get the model

Download its files with Hugging Face's command line:

pip install -U huggingface_hub
hf download Comfy-Org/Flux-2-Klein-4B

Then follow the usage in its model card. Nothing in this kit runs by itself.