What can I use flux-3-image-klein for?

Describe a scene with lettering and generate a picture containing that text; Supply a reference picture and request a recolored, replaced or removed element to get an edited picture; Supply several reference pictures and a scene description to create a combined composition

Can I run flux-3-image-klein on my computer?

It runs on your own hardware with a model runtime. Hardware requirements are not documented.

What do I need to use flux-3-image-klein?

Gated model access, compatible inference software, model components and a helper that expands prompts.

flux-3-image-klein: Generate and edit images (5.6B)

Model details

Original model black-forest-labs/flux-3-image-klein

Make/edit images

Input Image Output Image

Follow the model card setup Use through the Black Forest Labs API

Ways to use it Run locally · Use through an API

What it does

The model turns scene descriptions into pictures, edits supplied pictures and combines reference images into a composition. It can render writing inside an image. Boxes in a prompt guide where objects appear and how large they are, with written instructions controlling changes.

How to use it

Start with the model page’s reference-code instructions. Write your request and supply reference pictures for editing or composition. Expand the request into a full scene description using the supplied prompt helper or another language model. Run that description through compatible inference software to receive an image.

Common use cases

Describe a scene with lettering and generate a picture containing that text.
Supply a reference picture and request a recolored, replaced or removed element to get an edited picture.
Supply several reference pictures and a scene description to create a combined composition.

Can I use this?

Needs a model runtime on your computer

Requirements Complete gated access first and read the license. Download the model, text encoder and image autoencoder, then use compatible inference software. The reference code also loads a safety classifier and a prompt-expansion helper. Hardware requirements are not documented.

Caveat Boxes guide placement rather than strictly containing pixels. The download is a model package, not a complete application. For training or research, the source directs readers to the separate Base model.

Worth knowing Short prompts give generic output. The license permits noncommercial use and a commercial output exception for Qualifying Users, subject to its terms. Requires accepting the license on Hugging Face (free; access is granted automatically).

Why it's here

Not trending this week

Last seen on the Hugging Face trending list on 2 November 2026. It stays on BuildTube so you can still find it.

880 people have liked it on Hugging Face.
It was downloaded 180,515 times in the last 30 days.

Numbers checked on 8 November 2026; not refreshed since.

Behind it

View model page

BuildTube has not run or verified this project. Everything above is written from what the creator published.

Made this?

Quick questions

What is flux-3-image-klein?: The model turns scene descriptions into pictures, edits supplied pictures and combines reference images into a composition.
What can I use flux-3-image-klein for?: Describe a scene with lettering and generate a picture containing that text; Supply a reference picture and request a recolored, replaced or removed element to get an edited picture; Supply several reference pictures and a scene description to create a combined composition
Can I run flux-3-image-klein on my computer?: It runs on your own hardware with a model runtime. Hardware requirements are not documented.
What do I need to use flux-3-image-klein?: Gated model access, compatible inference software, model components and a helper that expands prompts.
What license does flux-3-image-klein use?: The license permits noncommercial use and a commercial output exception for Qualifying Users, subject to its terms. Complete gated access first and read the license.

More from this week

P-H3-Image-Comfy Make and edit 8-megapixel images in ComfyUI
Turn short text requests into 8-megapixel images and edit pictures on your own graphics card.
Added 7 Nov
Idol Turn one picture of an object into a 3D Gaussian splat
Idol turns one photo, render or generated image of an object into a 3D Gaussian splat file.
Runs in a terminalAdded 2 Nov
agent-desktop Let AI agents read and click desktop apps
For developers building computer-use agents: agent-desktop lets an AI agent read and operate desktop apps on Mac, Windows or Linux from a command line.
+13,858 stars this weekAdded 3 Nov

Related projects

flux-3-image-klein-comfy Make and edit images in ComfyUI (5.6B)
Same topic: image-generation
Added 22 Oct
P-H3-Image-Comfy Make and edit 8-megapixel images in ComfyUI
Same topic: image-generation
Added 7 Nov
Qwen-Image-2.1-viggle-turbo Make images about 5x faster with a distilled Qwen model
Same topic: diffusers
Needs a model setupAdded 1 Oct
Qwen-Image-2.1-Turbo Generate and edit images with an eight-step Qwen model
Same topic: diffusers
Needs a model setupAdded 10 Oct
Qwen-Image-2.1 Generate and edit images, including transparent layers, from text
Same topic: diffusers
Needs a model setupAdded 25 Sept
MOSS-Image-SFT Generate images with text and objects placed where you say
Same topic: diffusers
Added 21 Oct

Explore by topic

Post this

For makers

Made this? Show it’s on BuildTube — add the badge to your README or embed the card on your site.

README badge (Markdown)

[![Featured on BuildTube](https://buildtube.app/badge/hf-black-forest-labs-flux-3-image-klein.svg)](https://buildtube.app/p/hf-black-forest-labs-flux-3-image-klein/)

Embed card (HTML)

<iframe src="https://buildtube.app/embed/hf-black-forest-labs-flux-3-image-klein/" width="560" height="240" style="border:0;max-width:100%" loading="lazy" title="flux-3-image-klein on BuildTube"></iframe>