Private AI

Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Search
 
 
 
 
All conversations

Create

Chat
Studio

Explore

Models
Pricing
AI Apps
Blog

Library

Gallery
Workspace
Usage
API
Suggestions and bugs
Use cases

|

Terms

|

Privacy

|

Refunds
Balance
Subscription
Teams
Referrals
Presets
Settings
FAQPress & mediaBrand assetsBenchmarksEarn crypto
  1. Models
  2. Image
  3. Blackforestlabs

FLUX.3 Image Klein

Try Model

Black Forest Labs FLUX.3 Image Klein generates images with precise layout, style, and typography, or edits and composes up to ten references. Supports object placement, movement, removal, style transfer, and text editing. Optional labeled bounding boxes control the layout. Apply up to three FLUX.3 Klein-compatible .safetensors LoRAs with strengths from 0 to 4. LoRA requests use separate size-based pricing. Five square output sizes from 768px to 4K.

Added Oct 15, 2026

Details

Approx. Price
$0.009 per image
Model type
both

Settings

Generation controls available for this model.

Images Per Run

Up to 4

Output images

Input Images

Up to 10

Reference/edit images accepted • Route max 30 MB

Output Sizes

Square
up to 4,096px

Layout boxes (JSON)

Text

Default

N/A

JSON array of up to 32 objects. Each needs description; optional label and box: {x_min,y_min,x_max,y_max}. Editing also supports source_image_index (zero-based), source_box and target_box. Coordinates are fractions from 0 to 1. Reference labels in the prompt as <label>.

LoRA 1 Scale

Number

Default

1

Adapter strength from 0 to 4; default 1.

LoRA 1 URL

Text

Default

N/A

Optional direct URL to a FLUX.3 Klein-compatible .safetensors adapter. Other FLUX versions are incompatible. Adding a LoRA changes the image price.

LoRA 2 Scale

Number

Default

1

Adapter strength from 0 to 4; default 1.

LoRA 2 URL

Text

Default

N/A

Optional direct URL to a FLUX.3 Klein-compatible .safetensors adapter. Other FLUX versions are incompatible. Adding a LoRA changes the image price.

LoRA 3 Scale

Number

Default

1

Adapter strength from 0 to 4; default 1.

LoRA 3 URL

Text

Default

N/A

Optional direct URL to a FLUX.3 Klein-compatible .safetensors adapter. Other FLUX versions are incompatible. Adding a LoRA changes the image price.

Number of Images

Default

1

Output format

Select

Default

png

Options (3)

PNG, JPEG, WEBP

Showing 9 of 13 settings.

Benchmarks

Human preference benchmarks sourced from Artificial Analysis.

Text to Image

#22 / 106

ELO

1043.0

Appearances

5,224

95% CI

-12/12

Image Editing

#27 / 77

ELO

1072.0

Appearances

4,959

95% CI

-14/14

Release Date 2026-10 · Matched as FLUX 3 Image Klein

Artificial Analysis API

Examples

Loading examples…

Related image models

Compare FLUX.3 Image Klein with similar models from the same provider or model family.

FLUX.3 Image Klein Base

blackforestlabs/flux-3/klein/base/text-to-image

Black Forest Labs FLUX.3 Image Klein Base generates images with precise layout, style, and typography, or edits and composes up to ten references. Supports object placement, movement, removal, style transfer, and text editing. Optional labeled bounding boxes control the layout. Apply up to three FLUX.3 Klein-compatible .safetensors LoRAs with strengths from 0 to 4. LoRA requests use separate size-based pricing. Five square output sizes from 768px to 4K.

FLUX.2 [klein] 4B

flux-2-klein-4b

FLUX.2 [klein] 4B is a compact 4B-parameter text-to-image model from Black Forest Labs that delivers fast generation with quality results. Supports flexible sizing and JPEG, PNG, and WebP outputs.

FLUX.2 [klein] 9B

flux-2-klein-9b

FLUX.2 [klein] 9B is a high-quality 9B-parameter text-to-image model from Black Forest Labs with enhanced realism and crisper text rendering. Supports flexible sizing, JPEG/PNG/WebP output, and prompt-based edits with up to three reference images.

FLUX.1 Pro Erase

flux-pro/v1/erase

FLUX.1 Pro Erase by Black Forest Labs removes masked objects and text, filling the area with context-aware detail. Upload one image and a matching black-and-white mask: white removes, black preserves. Adjust mask expansion from 0 to 100 pixels and export JPEG or PNG. Accepts source images up to 4MP; larger outputs are resized to about 2MP. No text prompt is needed.

FLUX.3 Image

black-forest-labs/flux-3/text-to-image

Black Forest Labs FLUX.3 Image creates detailed photographs, illustrations, and designs with accurate typography. Upload up to 10 reference images to edit or combine them.

FLUX Virtual Try-On

flux-pro/v1/vto

Virtual try-on model that applies a garment reference image to a person image using styling instructions.