What is Flux.2 Klein?

Klein is the open-weights line of Black Forest Labs' Flux.2 generation, released in 9B and 4B sizes. It is the successor to the Flux.1 family that most open image models were built on.

No. Generation runs on our GPU pool, so a laptop or phone browser is enough. A 9B model locally means a large download and a card with the VRAM to hold it.

Which Klein sizes can I use?

Both 9B and 4B, plus the community checkpoints and LoRAs built on either, of which there are more than 2,100 on Civitai today.

Can I edit images with Klein, not just generate?

Yes. The Klein node in ComfyUI covers generation, editing, inpainting, outpainting and face swap in one place.

How does Klein compare with Flux.1?

Flux.1 still has by far the larger community — roughly 25,000 models on Civitai against 2,100 for Klein — so Flux.1 wins on ecosystem while Klein is the newer architecture. Both are here, so judge on your own prompt.

Can I import a Klein model from Civitai?

Yes. Paste the model URL and Diffus imports it — weights, previews and trigger words — then puts it in the generator.

Plans start at $1/month and every plan is credit-based, so the cost of a generation is visible before you run it.

Black Forest Labs' Flux.2 line

Run Flux.2 Klein in Your Browser

Klein 9B and 4B, plus the 2,100+ community models built on them. No 9-billion-parameter download, no GPU, no environment to keep alive.

The difference, not the spec sheet

Why Run Klein Here

The weights are open. What is not free is the disk, the card and the afternoon of setup.

2,100+ Klein Models, Already Hosted

Community checkpoints and LoRAs built on Klein 9B and 4B are on disk and selectable. Paste a Civitai link to add one that isn't.

Browse models

One Node, the Whole Workflow

Generate, edit, inpaint, outpaint and face swap from a single self-contained Klein node in ComfyUI — no graph to assemble before the first image.

Open ComfyUI

Compare It Against the Rest

Flux.1, Flux Kontext, Qwen, SDXL and SD 3.5 are in the same session. Run one prompt through several and keep what wins.

Start generating

Core capabilities

What You Can Do With It

Generation is the first step, not the whole job.

Prompt to picture

Text to Image on Klein

Prompt Klein 9B for quality or 4B when you want the lighter model, at the aspect ratio you need, with the sampler and guidance already tuned for the Flux.2 line.

Start generating

Edit where you generate

Edit, Inpaint and Outpaint

The Klein node covers editing in the same place you generate — repaint a region, extend the frame, swap a face — without exporting and losing the parameters.

Open ComfyUI

Bring your own LoRAs

Stack Community LoRAs

Klein has its own growing LoRA ecosystem on Civitai. Import one by URL and stack it, or fine-tune your own here and use it the moment training ends.

Browse models

How it works

Three Steps, No Setup

Nothing to download and no hardware to buy.

step 1

Pick Klein

Choose Klein 9B or 4B, or a community fine-tune built on either.

step 2

Write the Prompt

Or bring an image to edit — the same node handles both.

step 3

Generate and Refine

Inpaint, outpaint or upscale in place. Outputs land in your gallery.

Get started

Free creator tools

More Free Tools to Try

Single-purpose tools that need no setup. Describe it, click, done.

Flux 1 Image Generator

Text to image on the Flux.1 line, with community LoRAs.

Try for free

Flux Kontext Image Editor

Prompt-guided edits that keep character and style consistent.

Try for free

AI Image Generator

Text to image with community models, styles and aspect ratios.

Try for free

Explore the library

Models Built on Flux

Checkpoints and LoRAs across the Flux line, ready without a download.

A glamorous woman in a deep red sequin dress performing with a vintage microphone on a stage with a grand piano and dramatic lighting in a retro nightclub setting.

A cat girl character with black hair, green eyes, round rimless glasses, cat ears, and tail, wearing an off-shoulder green sweater, kneeling barefoot.

Link from the legend of Zelda BOTW [FLUX DEV] v1.0

A stylized white-haired girl with green eyes wearing a dark green overcoat stands in a snowy village at night with falling snow and illuminated lampposts.

Close-up portrait of a girl with long black hime-cut hair and red eyes drinking blood from a blood bag using a straw, dressed in a white coat and black shirt with a red necktie, set against a dimly lit dark background with soft shadows.

A detailed landscape painting forming a face silhouette with a snow-capped mountain ridge, an alpine lake reflecting dawn light on the left, and a shadowed pine forest with a chapel clearing on the right.

Cyberpunk stylized portrait of a bald woman with tribal patterns and big eyes, lit by pink and blue light with glasses and electrical wires attached.

MeMaXL Flat Anime Style - Noob/Illustrious/Pony/XL v4.0 B [Zootlustrious-v2]

Vanillaware Style | Anima/SDXL v2.0 [Zootlustrious-v2]

Cyberpunk(Photographic style) SDXL V.1.0

Get inspirations

Made on Diffus

Work from the community, with the model and prompt behind every image.

A young woman with blond hair crouching and holding a capsule toy in front of a row of capsule toy machines on a city street at night.

Two girls seated on a roller coaster at an amusement park; one is teary-eyed and excited, the other smiles confidently, both wearing blue outfits with white collars under bright daylight and a ferris wheel in the background.

Victorian albino girl in a flowing burgundy dress running on a foggy cobbled London street at night, pursued by a large dark, eldritch creature with glowing eyes.

A grotesque skeletal figure with glowing red eyes wearing a golden skull mask and dark flowing cloth, adorned with a bone-like golden crown and occult charms, set against a dark abstract backdrop.

A forest nymph wearing a living vine and flower crown, with long flowing hair and a cloak adorned with leaves and silver decorations.

A dark fantasy shadow knight with glowing red eyes and a red orb on chest, wearing horned armor with intricate details in a cinematic manga style.

A gritty manga sketch of a horned goddess of war with black skin, glowing white eyes, busty armored chest, a weathered spiked pauldron, and flowing hair set against a white background with volumetric lighting effects.

A detailed court portrait oil painting-style image showing a young Spanish princess in a black and royal blue velvet gown embroidered with gold, standing in a grand marble ballroom under an ornate chandelier.

A fierce woman warrior wielding a glowing blue katana with red eyes, short black hair, wearing black pants and a white top, surrounded by fiery sparks in an anime style illustration.

Detailed oil painting of a teen female angel with flowing red hair, blue eyes, white feathery wings, and an ornate black and silver dress, lit with Rembrandt lighting.

A massive futuristic sci-fi structure with a glowing orange backdrop, a man standing on rocky terrain observing it.

A veiled empress wearing an ornate crown with horns stands solemnly against a dark stormy sky filled with lightning, her glowing red eyes visible above her dark veil and cloak.

Photorealistic Victorian lady in an ornate gown walking along a misty cobblestone manor walkway at dawn, holding a lace parasol under soft early morning light.

A giant white goose with several long necks and heads resembling a hydra, all of which are aggressively honking.

A serene sunrise beach scene on Koh Yao Noi island featuring a person on a hanging swing between two giant palms, with turquoise ocean water and lush rock formations.

Close-up of a golden foot glowing with shimmering particles, stepping onto a dark granular surface illuminated with warm light and blurred amber orbs in the background.

$A lone silhouetted figure stands on a rocky ridge beneath a glowing celestial orb with a fractured corona, surrounded by swirling cosmic gas and dark clouds.$