# FLUX.2 [klein] 4B

> Black Forest Labs' compact, open-source image generation model with sub-second inference, optimized for production and near real-time applications with multi-reference support

## Quick Reference

- Model ID: flux.2-klein-4b
- Creator: Black Forest Labs
- Status: active
- Family: flux.2
- Base URL: https://api.lumenfall.ai/openai/v1

## Specifications

- Max Resolution: 2048x2048
- Max Input Images: 4
- Input Modalities: text, image
- Output Modalities: image
- Supported Modes: Text to Image, Image Edit

## API Parameters

The compiled parameter schema for this model is available via the API: `GET /v1/models/flux.2-klein-4b?schema=true`.

### Core Parameters

- `prompt` (string) — REQUIRED: Edit instruction for the image. Modes: Image Edit, Text to Image
- `seed` (integer): Random seed for reproducibility. Modes: Image Edit, Text to Image

### Size & Layout

- `size` (string): Image dimensions as WxH pixels (e.g. "1024x1024") or aspect ratio (e.g. "16:9"). Values: auto, 1563x670, 670x1564, 1365x768, 768x1365, 1254x836, 836x1254, 887x1182, 1024x1024, 1145x916, 916x1145, 1183x887. Modes: Image Edit, Text to Image
- `aspect_ratio` (string): Aspect ratio of the output image (e.g. "16:9", "1:1"). Values: auto, 9:21, 9:16, 2:3, 3:4, 4:5, 1:1, 5:4, 4:3, 3:2, 16:9, 21:9. Modes: Image Edit, Text to Image
- `resolution` (string): Output resolution tier (e.g. "1K", "4K"). Values: auto, 1K. Modes: Image Edit, Text to Image

### Media Inputs

- `image` (file) — REQUIRED: Input image(s) to edit. Modes: Image Edit

### Output & Format

- `response_format` (string): How to return the image. Default: url. Values: url, b64_json. Modes: Image Edit, Text to Image
- `output_format` (string): Output image format. Values: png, jpeg, gif, webp, avif. Modes: Image Edit, Text to Image
- `output_compression` (integer): Compression level for lossy formats (JPEG, WebP, AVIF). Modes: Image Edit, Text to Image
- `n` (integer): Number of images to generate. Default: 1. Modes: Image Edit, Text to Image

### Additional Parameters

- `disable_safety_checker` (boolean): Disable safety checker for generated images.. Modes: Text to Image, Image Edit. Only available via replicate
- `enable_safety_checker` (boolean): If set to true, the safety checker will be enabled.. Modes: Image Edit, Text to Image. Only available via fal
- `go_fast` (boolean): Run faster predictions with additional optimizations.. Modes: Text to Image, Image Edit. Only available via replicate
- `num_inference_steps` (integer): The number of inference steps to perform.. Modes: Image Edit, Text to Image. Only available via fal
- `output_megapixels` (string): Resolution of the output image in megapixels. Values: 0.25, 0.5, 1, 2, 4. Modes: Text to Image, Image Edit. Only available via replicate
- `output_quality` (integer): Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs.. Modes: Text to Image, Image Edit. Only available via replicate
- `sync_mode` (boolean): If `True`, the media will be returned as a data URI. Output is not stored when this is True.. Modes: Image Edit, Text to Image. Only available via fal


## Model Identifiers

- Primary Slug: flux.2-klein-4b
- Aliases: flux-2-klein-4b

## Dates

- Released: January 2026

## Tags

image-generation, text-to-image, image-editing, open-weights

## Available Providers

### fal.ai

- Config Key: fal/flux.2-klein-4b-edit
- Provider Model ID: fal-ai/flux-2/klein/4b/edit
- Pricing: $0.010/megapixel, $0.010/megapixel
  - Source: https://fal.ai/models/fal-ai/flux-2/klein/4b/edit

### Replicate

- Config Key: replicate/flux.2-klein-4b
- Provider Model ID: black-forest-labs/flux-2-klein-4b
- Pricing: $0.0010/megapixel, $0.0010/megapixel
  - Source: https://replicate.com/black-forest-labs/flux-2-klein-4b

### fal.ai

- Config Key: fal/flux.2-klein-4b
- Provider Model ID: fal-ai/flux-2/klein/4b
- Pricing: $0.0050/megapixel
  - Source: https://fal.ai/models/fal-ai/flux-2/klein/4b


## Performance Metrics

Provider performance over the last 30 days.

### fal

- Median Generation Time (p50): 3517ms
- 95th Percentile Generation Time (p95): 15869ms
- Average Generation Time: 5507ms
- Success Rate: 100.0%
- Total Requests: 11
- Time to First Byte (p50): 971ms
- Time to First Byte (p95): 24819ms


## Arena Benchmarks

### Modern Clean Menu

- Elo: 1227
- Record: 1W / 2L / 1T (4 battles)
- Rank: #7 of 69

### Geometric Composition

- Elo: 1177
- Record: 7W / 2L / 2T (11 battles)
- Rank: #32 of 70

### The Halloween Invitation

- Elo: 1157
- Record: 8W / 5L / 0T (13 battles)
- Rank: #26 of 70

### Pose & Character Mashup

- Elo: 1146
- Record: 4W / 3L / 0T (7 battles)
- Rank: #6 of 33

### Man and Car in California

- Elo: 1145
- Record: 3W / 1L / 1T (5 battles)
- Rank: #22 of 35

### The Reversed Rodeo

- Elo: 1123
- Record: 3W / 6L / 0T (9 battles)
- Rank: #28 of 68

### Chalkboard Menu

- Elo: 1112
- Record: 5W / 3L / 0T (8 battles)
- Rank: #39 of 69

### Adorable Baby Animals in Sunny Meadow

- Elo: 1112
- Record: 2W / 5L / 0T (7 battles)
- Rank: #53 of 72

### Magic Burger Explosion: Fiery Photorealism Challenge

- Elo: 1084
- Record: 2W / 3L / 0T (5 battles)
- Rank: #53 of 69

### The Capybara Taxi Driver

- Elo: 1076
- Record: 3W / 1L / 1T (5 battles)
- Rank: #52 of 69

### Candid Street Photography

- Elo: 1066
- Record: 1W / 5L / 0T (6 battles)
- Rank: #58 of 68

### Fantasy Warrior

- Elo: 1014
- Record: 0W / 4L / 0T (4 battles)
- Rank: #63 of 71

### Vintage Cafe Logo

- Elo: 994
- Record: 0W / 5L / 1T (6 battles)
- Rank: #70 of 70


## Use Cases & Category Performance

### Art (Text-to-Image)

- Rank: #22 of 57
- Elo: 1191
- Record: 11W / 11L / 0T (22 battles)
- Win Rate: 50.0%

### Lighting, Shadows & Materials (Image Editing)

- Rank: #18 of 36
- Elo: 1207
- Record: 10W / 8L / 2T (20 battles)
- Win Rate: 50.0%

### Face & Identity (Image Editing)

- Rank: #19 of 32
- Elo: 1141
- Record: 3W / 1L / 0T (4 battles)
- Win Rate: 75.0%

### Preservation (Image Editing)

- Rank: #22 of 37
- Elo: 1183
- Record: 12W / 11L / 2T (25 battles)
- Win Rate: 48.0%

### Aesthetics (Image Editing)

- Rank: #21 of 33
- Elo: 1155
- Record: 4W / 5L / 2T (11 battles)
- Win Rate: 36.4%

### Product, Branding & Commercial (Text-to-Image)

- Rank: #39 of 61
- Elo: 1203
- Record: 16W / 20L / 2T (38 battles)
- Win Rate: 42.1%

### People & Poses (Image Editing)

- Rank: #18 of 27
- Elo: 1147
- Record: 4W / 5L / 1T (10 battles)
- Win Rate: 40.0%

### Photorealism (Image Editing)

- Rank: #24 of 36
- Elo: 1178
- Record: 6W / 5L / 2T (13 battles)
- Win Rate: 46.2%

### Prompt Adherence (Text-to-Image)

- Rank: #42 of 62
- Elo: 1208
- Record: 23W / 25L / 4T (52 battles)
- Win Rate: 44.2%

### Text Rendering (Text-to-Image)

- Rank: #42 of 61
- Elo: 1197
- Record: 16W / 21L / 2T (39 battles)
- Win Rate: 41.0%

### Adding & Editing Objects (Image Editing)

- Rank: #21 of 29
- Elo: 1153
- Record: 4W / 3L / 1T (8 battles)
- Win Rate: 50.0%

### Prompt Adherence (Image Editing)

- Rank: #21 of 29
- Elo: 1175
- Record: 6W / 6L / 0T (12 battles)
- Win Rate: 50.0%

### 3D Imaging & Modeling (Text-to-Image)

- Rank: #44 of 61
- Elo: 1157
- Record: 7W / 3L / 2T (12 battles)
- Win Rate: 58.3%

### Photorealism (Text-to-Image)

- Rank: #46 of 62
- Elo: 1162
- Record: 23W / 29L / 3T (55 battles)
- Win Rate: 41.8%

### Aesthetics (Text-to-Image)

- Rank: #48 of 62
- Elo: 1195
- Record: 27W / 39L / 5T (71 battles)
- Win Rate: 38.0%

### Artistic Restyling (Image Editing)

- Rank: #22 of 28
- Elo: 1098
- Record: 2W / 3L / 0T (5 battles)
- Win Rate: 40.0%

### Creativity (Image Editing)

- Rank: #22 of 28
- Elo: 1098
- Record: 2W / 3L / 0T (5 battles)
- Win Rate: 40.0%

### Backgrounds & Scenes (Image Editing)

- Rank: #21 of 26
- Elo: 1128
- Record: 3W / 1L / 1T (5 battles)
- Win Rate: 60.0%

### Creativity (Text-to-Image)

- Rank: #55 of 62
- Elo: 1162
- Record: 11W / 23L / 1T (35 battles)
- Win Rate: 31.4%

### Portraits (Text-to-Image)

- Rank: #48 of 50
- Elo: 1015
- Record: 0W / 4L / 0T (4 battles)
- Win Rate: 0.0%

### Cartoon, Anime & Fantasy (Text-to-Image)

- Rank: #48 of 50
- Elo: 1015
- Record: 0W / 4L / 0T (4 battles)
- Win Rate: 0.0%


## Image Gallery

17 images available for this model. Browse all at https://lumenfall.ai/models/black-forest-labs/flux.2-klein-4b/gallery

### Curated Examples

- [A cinematic, wide-angle shot of a high-end, minimalist luxury boutique at dusk. The storefront fe...](https://assets.lumenfall.ai/Gs49uwhZZN2OOWBVU1lRSGcuIJ6aLp2ImNXk3H1WgLI/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/66cmc8xq5wo9zgds13qitr1rx68n@jpeg)
- [An ethereal macro photograph of a single translucent dandelion seed resting on a calm, dark obsid...](https://assets.lumenfall.ai/wGWV_gMzmLehFjcMdJg99ZTKeKkf6wdq5s6DZu1xIJc/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/zcz7tfbqrvirlmvalqlue77n86d4@jpeg)
- [A highly detailed, macro photograph of a weathered leather craftsman's workbench. In the center s...](https://assets.lumenfall.ai/cuUzzw7AMb8JY7jrk02zLgN4y9fFdelF7XdA6mxXtsE/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/3kz7oaduvbgfmg6wvepiyedzlylv@jpeg)
- [A rustic wooden storefront of a boutique bakery named "CRUST & CO." in elegant gold serif letteri...](https://assets.lumenfall.ai/afrFooKKTTVFFOobuZCHXXs0jkOjAP01V5Km7RtX6b0/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/ikkzci1ebbtrp2k816qzfo83a6pp@jpeg)

### Arena Competition Results

- [Modern Clean Menu](https://assets.lumenfall.ai/G4o8c0AY4unyKnjIR8n9symsX6ZnPcaCnNXL6_pMO9o/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/th2mgeqchnn2lzalwws7cb4i6e5e@jpeg): #7 of 69 (Elo 1227)
- [Geometric Composition](https://assets.lumenfall.ai/kOYgeUVTgQi9Y99qc9GiKJrvcRinQDnTP1FkX7QnnO4/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/zzcfoppq6vyzefdmriub9l7tzmq2@jpeg): #32 of 70 (Elo 1177)
- [The Halloween Invitation](https://assets.lumenfall.ai/p8prgAQf9v7ZTtrTFcktCKi4OCaSeUeI4TLufF1RVC4/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/u33uc79zbn7ktufizrty7rofndi3@jpeg): #25 of 70 (Elo 1157)
- [Pose & Character Mashup](https://assets.lumenfall.ai/yUQ84GtYzV6Naes4eHNhUA6FW5G9qJMySxA5PqTuKfA/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/gp742sjywy2darnay5ozppaew9wd@jpeg): #6 of 33 (Elo 1146)
- [Man and Car in California](https://assets.lumenfall.ai/8OHLGkgg8-8aU67lCQ02mGSOEr896qFaewgZL2gYKZM/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/nbhg80r80vcbqkv7wloz7ulvmk5j@jpeg): #22 of 35 (Elo 1145)
- [The Reversed Rodeo](https://assets.lumenfall.ai/YtBYJb5pSloQON1Jhl_B7TjjxArHqn-EXKSO-ImUy0I/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/1t0noxmrschh0w43x76aciyhtgx7@jpeg): #28 of 68 (Elo 1123)
- [Fantasy Warrior](https://assets.lumenfall.ai/3r0kFXKkdGKuuR1xgzGfuzXLReUBFNJv_G9U_xMTa-0/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/1u9bcx7ydkn0a70xdzum6f46sz3g@jpeg): #45 of 71 (Elo 1113)
- [Chalkboard Menu](https://assets.lumenfall.ai/e9dSHJGhWHGCfz34z5C9AEJHyD-x2mqwOlnRXfz4gOE/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/qmkt7ydojt3hbjxd8hhba4yd5r58@jpeg): #39 of 69 (Elo 1112)
- [Adorable Baby Animals in Sunny Meadow](https://assets.lumenfall.ai/qMHFnDmanYD5kppvQYgKKmwrQ4zBJLBgqUuBvJgOJ0c/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/o0fszfb06rq9pca6y7wij05v0rs9@jpeg): #53 of 72 (Elo 1112)
- [Magic Burger Explosion: Fiery Photorealism Challenge](https://assets.lumenfall.ai/gtd6I5Q9Ny3q2tCujOBJ9mBsMxl1vd3B5-mieP1KKBs/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/uilhh3b86qay23ooagg0art1pax9@jpeg): #53 of 69 (Elo 1084)
- [The Capybara Taxi Driver](https://assets.lumenfall.ai/B2YeztXOC8HvQsuwEPcE5noxdrUzyiN7oxfzm6O3qa4/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/91nopmblq4fhbiv5q1y74fpzxl73@jpeg): #53 of 69 (Elo 1076)
- [Candid Street Photography](https://assets.lumenfall.ai/51h7xQE11_RDWlbJdRqklO1ZjXloQM-A7hcL_vcuAYA/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/ki4qjrai6mv7bs9f9o4pew4wfuj6@jpeg): #58 of 68 (Elo 1066)
- [Vintage Cafe Logo](https://assets.lumenfall.ai/9Wmb5VGn8ZuWXskk7CrlEKHxpjcdC5VkUrtoJT4mkF8/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/2uegvfwzh44arg5pnn6x68fc6zkp@jpeg): #70 of 70 (Elo 994)

## Example Prompt

The following prompt was used to generate an example image in our playground:

A rustic wooden storefront of a boutique bakery named "CRUST & CO." in elegant gold serif lettering. Through the large glass window, a small capybara sits quietly on a floor rug near a display of sourdough bread. Low morning sun, cinematic.

## Code Examples

### Text to Image (/v1/images/generations)

#### cURL

curl -X POST \
  https://api.lumenfall.ai/openai/v1/images/generations \
  -H "Authorization: Bearer $LUMENFALL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "flux.2-klein-4b",
    "prompt": "",
    "size": "1024x1024"
  }'

# Response:
# { "created": 1234567890, "data": [{ "url": "https://...", "revised_prompt": "..." }] }

#### JavaScript

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://api.lumenfall.ai/openai/v1'
});

const response = await client.images.generate({
  model: 'flux.2-klein-4b',
  prompt: '',
  size: '1024x1024'
});

// { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }
console.log(response.data[0].url);

#### Python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.lumenfall.ai/openai/v1"
)

response = client.images.generate(
    model="flux.2-klein-4b",
    prompt="",
    size="1024x1024"
)

# { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }
print(response.data[0].url)

### Image Edit (/v1/images/edits)

#### cURL

curl -X POST \
  https://api.lumenfall.ai/openai/v1/images/edits \
  -H "Authorization: Bearer $LUMENFALL_API_KEY" \
  -F "model=flux.2-klein-4b" \
  -F "image=@source.png" \
  -F "prompt=Add a starry night sky to this image" \
  -F "size=1024x1024"

# Response:
# { "created": 1234567890, "data": [{ "url": "https://...", "revised_prompt": "..." }] }

#### JavaScript

import OpenAI from 'openai';
import fs from 'fs';

const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://api.lumenfall.ai/openai/v1'
});

const response = await client.images.edit({
  model: 'flux.2-klein-4b',
  image: fs.createReadStream('source.png'),
  prompt: 'Add a starry night sky to this image',
  size: '1024x1024'
});

// { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }
console.log(response.data[0].url);

#### Python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.lumenfall.ai/openai/v1"
)

response = client.images.edit(
    model="flux.2-klein-4b",
    image=open("source.png", "rb"),
    prompt="Add a starry night sky to this image",
    size="1024x1024"
)

# { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }
print(response.data[0].url)


## Frequently Asked Questions

### How much does FLUX.2 [klein] 4B cost?

FLUX.2 [klein] 4B starts at $0.001 per image through Lumenfall. Pricing varies by provider. Lumenfall does not add any markup to provider pricing.

### How do I use FLUX.2 [klein] 4B via API?

You can use FLUX.2 [klein] 4B through Lumenfall's OpenAI-compatible API. Send requests to the unified endpoint with model ID "flux.2-klein-4b". Code examples are available in Python, JavaScript, and cURL.

### Which providers offer FLUX.2 [klein] 4B?

FLUX.2 [klein] 4B is available through fal.ai and Replicate on Lumenfall. Lumenfall automatically routes requests to the best available provider.

### What is the maximum resolution for FLUX.2 [klein] 4B?

FLUX.2 [klein] 4B supports images up to 2048x2048 resolution.

## Links

- Model Page: https://lumenfall.ai/models/black-forest-labs/flux.2-klein-4b
- About: https://lumenfall.ai/models/black-forest-labs/flux.2-klein-4b/about
- Providers, Pricing & Performance: https://lumenfall.ai/models/black-forest-labs/flux.2-klein-4b/providers
- API Reference: https://lumenfall.ai/models/black-forest-labs/flux.2-klein-4b/api
- Benchmarks: https://lumenfall.ai/models/black-forest-labs/flux.2-klein-4b/benchmarks
- Use Cases: https://lumenfall.ai/models/black-forest-labs/flux.2-klein-4b/use-cases
- Gallery: https://lumenfall.ai/models/black-forest-labs/flux.2-klein-4b/gallery
- Playground: https://lumenfall.ai/models/black-forest-labs/flux.2-klein-4b/playground
- API Documentation: https://docs.lumenfall.ai