bfl/flux-2/klein/9b/edit/lora
Flux 2 Klein 9b is BFL's intelligent image editing model. Transform, retouch, and reimagine existing images using text prompts - from background replacement to artistic style conversion.
PNG, JPEG, WebP, or GIF · 20 MiB maximum each
Example output — click Run to generate your own
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
https://api.sandbase.ai/v1/runbfl/flux-2/klein/9b/edit/loraInput Schema
7 parameters · 1 required · 6 optional
| Parameter | Type | Required | Description |
|---|---|---|---|
prompt | string | Required | The prompt to edit the image. |
seed | integer | Optional | The seed to use for the generation. If not provided, a random seed will be used. |
loras | object[] | Optional | List of LoRA weights to apply (maximum 3). · Default: [] |
images | string[] | Optional | The URLs of the images for editing. A maximum of 4 images are allowed. |
aspect_ratio | string | Optional | The aspect ratio of the generated image. · Options: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16 21:916:93:24:35:41:14:53:42:39:16 |
output_format | string | Optional | The format of the generated image. · Options: jpeg, png · Default: "png" jpegpng |
num_inference_steps | integer | Optional | The number of inference steps to perform. · Min: 4 · Max: 8 · Default: 4 |
Output Schema
| Field | Type | Description |
|---|---|---|
id | string | Unique identifier for the generation task |
status | string | Task status: pending, running, completed, failed, timeout |
model | string | Model used for the generation |
outputs | array | Array of output items |
outputs[].url | string | URL of the generated artifact |
outputs[].content_type | string | MIME type (e.g. image/png, video/mp4) |
error | object | null | Error details if failed, null on success |
error.type | string | Machine-readable error type code |
error.message | string | Human-readable error description |
Async Workflow
This model uses asynchronous execution. Submit a request and poll for the result.
- Submit — POST to /v1/run, receive an
id - Poll — GET /v1/run/{id} until status is
completed,failed, ortimeout - Retrieve — Read
outputsfrom the completed response
Code Examples
Ready-to-run snippets
# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "bfl/flux-2/klein/9b/edit/lora",
"loras": [],
"images": [
"https://static.sandbase.ai/examples/bfl/flux-2/klein/9b/edit/lora/input_images_0.png"
],
"prompt": "Turn this into a realistic image",
"output_format": "png",
"num_inference_steps": 4
}'
# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
-H "Authorization: Bearer YOUR_API_KEY"API README
FLUX.2 [klein] 9B LoRA
FLUX.2 [klein] 9B LoRA Edit reimagines existing images from text prompts. Its editing range includes background replacement and artistic style conversion, while multiple references can carry several visual cues into one revision.
This variant accepts image and LoRA inputs and uses a compact 4–8 inference-step range. Ten aspect ratios, JPEG or PNG output, and seed control support repeatable delivery once a visual direction has been selected.
Highlights
Background replacement. Reposition an existing subject in a new setting without rebuilding the complete image.
Artistic style conversion. Use written direction to move supplied imagery toward a different visual treatment.
LoRA and reference inputs. Combine LoRA inputs with several reference images when the edit needs multiple forms of visual direction.
Compact production controls. Use 4–8 inference steps, ten aspect ratios, JPEG or PNG output, and a seed for controlled reruns.
Pricing
| Billing unit | Price |
|---|---|
| Per request | $0.03 |
When to Use
| ✅ Good fit | ❌ Consider alternatives |
|---|---|
| The model's named workflow matches the source material and intended output | A different input modality or model route is required |
| A managed asynchronous result is suitable for the production pipeline | A synchronous, interactive editor is essential |
| The documented controls cover the required duration, framing, or format | The project needs controls outside this endpoint's schema |
| Creative iteration benefits from a repeatable request structure | Exact deterministic pixels, frames, geometry, or samples are mandatory |
| A finished downloadable media asset is the desired deliverable | Editable source layers or a native project file are required |
Prompt Guide
For generation, state the intended result first, then add the subject or source treatment, progression, style, and delivery constraints. Keep one creative variable per phrase, use the documented field names for controls, and change one setting at a time when comparing results.
{
"aspect_ratio": "21:9",
"images": [
"https://example.com/reference-1.png",
"https://example.com/reference-2.png"
],
"output_format": "png",
"prompt": "Turn this into a realistic image"
}
Technical Specs
| Spec | Value |
|---|---|
| Model ID | bfl/flux-2/klein/9b/edit/lora |
| Inputs | aspect_ratio, images, loras, num_inference_steps, output_format, prompt, seed |
| Required inputs | prompt |
| Output fields | content_type, url |
| Execution | Async (submit, then poll for result) |
| Aspect Ratio | 21:9 / 16:9 / 3:2 / 4:3 / 5:4 / 1:1 / 4:5 / 3:4 / 2:3 / 9:16 |
| Output Format | jpeg / png |
Related Models
bfl/flux-2/klein/9b/edit— Compare this concrete local family route.bfl/flux-2/klein/9b— Compare this concrete local family route.bfl/flux-2/klein/9b/base— Compare this concrete local family route.

