FLUX.2 [klein] 4B LoRA

Name: FLUX.2 [klein] 4B LoRA
Author: BFL

bfl/flux-2/klein/4b/edit/lora

Flux 2 Klein 4b is BFL's intelligent image editing model. Transform, retouch, and reimagine existing images using text prompts - from background replacement to artistic style conversion.

Use in agent Get API key

Base price: $0.02USD / run
Execution: async
Model type: image
Input fields: 7

Try the model

Playground

Open playground

Input

Prompt(string)

The prompt to edit the image.

Image URL or upload(array)

Upload

PNG, JPEG, WebP, or GIF · 20 MiB maximum each

The URLs of the images for editing. A maximum of 4 images are allowed.

Output Format(string)

The format of the generated image. Allowed values: jpeg, png.

Aspect Ratio(string)

The aspect ratio of the generated image. Allowed values: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16.

Seed(integer)

The seed to use for the generation. If not provided, a random seed will be used.

Loras(array)

Enter a JSON array.

Num Inference Steps(integer)

Range: 4 to 8.

OutputReady

Your output will appear here

Complete the inputs, then click Run.

Specifications

Pricing

Base price: $0.02 / run

Context & modalities

Input: Schema-defined
Output: image

Capabilities

Chat: Not supported
Vision: Not supported
Reasoning: Not supported
Structured output: Not supported
Function calling: Not supported
Audio input: Not supported

Access

Provider: BFL
Model ID: bfl/flux-2/klein/4b/edit/lora
Execution: async
API: Unified Run API
Endpoint: /v1/run

API README

FLUX.2 [klein] 4B LoRA

FLUX.2 [klein] 4B LoRA exposes the FLUX.2 Klein 4B Edit LoRA capability for reference-led image revision. The step-distilled model is built for low-latency inference while retaining strong visual quality. A lightweight adapter adds a learned style, subject, or domain concept to this exact path.

Use this 4B route when accessibility, local efficiency, and rapid iteration matter. Describe the requested change separately from source identity, geometry, and regions that must remain fixed.

Highlights

FLUX.2 Klein 4B Edit LoRA architecture. Uses the compact step-distilled 4B model for fast visual synthesis.
Unified contextual editing. Understands source content and applies directed semantic or appearance changes.
Adapter-based specialization. Expresses a learned style, character, object, or domain through a lightweight adaptation.
Reference consistency. Preserves important subject, composition, and detail through the requested revision.

Pricing

Configuration	Billing unit	Price
Base generation	Per request	$0.02

When to Use

✅ Good fit	❌ Consider alternatives
The project needs this exact generation or editing route	The intended task belongs to video, audio, or 3D media
Available references match every required local field	Required source assets or rights are unavailable
The brief can specify composition, color, and finish	Output must be deterministic at pixel level
Supported dimensions and formats fit final placement	Delivery requires unsupported canvas specifications
An asynchronous generated image fits production	A live frame-synchronous response is mandatory

Prompt Guide

Write a complete visual brief: identify the subject and references, define composition and viewpoint, describe lighting, palette, materials, typography, and finish, then list exact preservation constraints. FLUX.2 Klein does not rely on prompt upsampling, so use clear descriptive sentences rather than sparse keywords.

{
  "prompt": "A photorealistic editorial composition with precise subject placement, controlled lighting, exact colors, and clean typography",
  "seed": 1,
  "loras": [],
  "images": [
    "https://example.com/reference.jpg"
  ]
}

Technical Specs

Spec	Value
Model ID	`bfl/flux-2/klein/4b/edit/lora`
Input fields	`seed` (integer)<br>`loras` (array)<br>`images` (array)<br>`prompt` (string)<br>`aspect_ratio` (string; `21:9`, `16:9`, `3:2`, `4:3`, `5:4`, `1:1`, `4:5`, `3:4`, `2:3`, `9:16`)<br>`output_format` (string; `jpeg`, `png`)<br>`num_inference_steps` (integer; 4–8)
Required input	`prompt`
Output fields	`url`, `content_type`
Execution	Asynchronous job

Related Models

bfl/flux-2/klein/4b
bfl/flux-2/klein/4b/base
bfl/flux-2/klein/4b/base/edit

Start building

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

Production API

Unified Run API endpoint

https://api.sandbase.ai/v1/run

Model ID

bfl/flux-2/klein/4b/edit/lora

# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
  -X POST "https://api.sandbase.ai/v1/run" \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'SANDBASE_JSON'
{
  "model": "bfl/flux-2/klein/4b/edit/lora",
  "loras": [],
  "images": [
    "https://static.sandbase.ai/examples/bfl/flux-2/klein/4b/edit/lora/input_images_0.png"
  ],
  "prompt": "Turn this into a realistic image",
  "output_format": "png",
  "num_inference_steps": 4
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
  status=$(printf '%s' "$result" | jq -r .status)
  case "$status" in completed|failed|timeout) break ;; esac
  sleep 2
  result=$(curl --fail-with-body --silent \
    -H "Authorization: Bearer $SANDBASE_API_KEY" \
    "https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"

Choose your model

Compare models

All language models

Model	Context	Input / 1M	Output / 1M	Released
FLUX.2 [klein] 4B LoRAThis model `BFL`	—	—	—	Mar 17, 2026
FLUX Virtual Try-On `BFL`	—	—	—	May 28, 2026
Flux Pro Erase `BFL`	—	—	—	May 21, 2026
Flux 2 Pro `BFL`	—	—	—	May 14, 2026
FLUX.2 [klein] 9B LoRA `BFL`	—	—	—	Mar 17, 2026
FLUX.2 [klein] 9B LoRA `BFL`	—	—	—	Mar 17, 2026