Introduction
FLUX.2 Klein 9B LoRA Image editing changes one to three source images from a written instruction on Black Forest Labs' step-distilled FLUX.2 [klein] 9B, with up to three of your own LoRA files loaded. Keep the source shape with auto or pick one of nine shapes at 1k or 2k. Most edits took about ten seconds of model time, there is no mask or strength control to tune, and nothing is filtered.
Choose a mode by starting material
| What you have | Mode |
|---|---|
| a written description and a LoRA | FLUX.2 Klein 9B LoRA Text to image |
| one to three images to change | FLUX.2 Klein 9B LoRA Image editing |
Key features
Same person, new scene
In our tests the face and hair carried through changes of outfit and place: a man on a park bench in a hoodie came back on a car park roof at dusk in an open-collar shirt, still clearly the same person.
Up to three sources
Two head-and-shoulders portraits taken apart became one couple at a lit fountain, each keeping their face. With two or three sources, faces and hair can drift a little, so check each person before you use the result.
LoRAs on edits
A film or analog LoRA sets the grade of the edited picture.
Request parameters
| Parameter | Required | Description |
|---|---|---|
aspect_ratio | No | The shape of the frame: wide, square or tall. auto · 1:1 · 16:9 · 9:16 · 4:3 · 3:4 · 3:2 · 2:3 · 21:9 · 9:21 · Default: auto |
image_urls | Yes | Photos to edit or combine. Say in the prompt what each one adds. |
loras | No | Load your own LoRA files to lock in a style or character. Default: [] |
prompt | Yes | Say what to change and what must stay the same. Put a LoRA trigger phrase first. |
resolution | No | Output size. Bigger sizes look sharper and cost more. 1k · 2k · Default: 1k |
seed | No | Reuse the same number to get a repeatable result. ≥ 0 · ≤ 2147483647 |
Pricing
Prices are in credits, the same credits you use on the website (1 credit = $0.01). The hold is taken when the task is accepted and settled to the actual charge when it finishes; failed tasks are refunded.
| Option | Credits per image | ≈ USD |
|---|---|---|
| Standard | 3.78 | $0.038 |
Each task is rounded up to whole credits, so one run at the lowest tier costs 4 credits per image ($0.04).
For an exact number before you run, send the same body to POST /jobs/quote.
Use cases
Wardrobe and location changes
Move a person into a new place and outfit in one pass while keeping their likeness, for lookbooks, mood boards and character sheets.
Putting people together
Combine two or three portraits into one scene, then restyle the result with a LoRA so the series matches.
Fast retouch rounds
At about ten seconds per edit you can try several instructions and LoRA strengths on the same photo and keep the best version, instead of settling for the first attempt.
Prompt guide & pro tips
Protect first, then change
Start the instruction with what must stay the same, such as face, hair and expression, then describe the change in concrete terms: the garment, the place and the light. Short, specific instructions held faces better than long lists in our tests.
Give each source a role
With several images, say what each one brings: the woman from the first image, the man from the second, the room from the third. The order in your prompt should match the upload order.
Lower a LoRA that changes faces
If the person stops looking like the source, take the LoRA scale down by 0.2 and run the same seed again. Anatomy LoRAs are the usual cause; style LoRAs rarely move a face.
API quick start
Call the FLUX.2 Klein 9B LoRA API in three steps
- Create an API key. Sign in to PopNow and create a key in the API console. Keys start with sk-popnow- and use the same credits as the website.
- Send the request. POST /jobs/createTask with model black-forest-labs/flux-2-klein-9b-lora/edit and an input object that follows the parameter table. The response returns a task ID straight away.
- Get the result. Poll GET /jobs/recordInfo with the task ID, or pass a callBackUrl and we post the result to it. Download the output links when the task succeeds.
# 1. Create the task. Keep the Idempotency-Key if you retry after a network error.
export IDEMPOTENCY_KEY="$(uuidgen)"
curl -X POST https://api.popnow.ai/api/v1/jobs/createTask \
-H "Authorization: Bearer $POPNOW_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $IDEMPOTENCY_KEY" \
-d '{
"model": "black-forest-labs/flux-2-klein-9b-lora/edit",
"input": {
"prompt": "A ceramic teapot on a linen cloth, soft window light, muted palette",
"image_urls": [
"https://media.popnow.ai/influencer/examples/marco.webp"
],
"aspect_ratio": "auto",
"resolution": "1k"
}
}'
# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
-H "Authorization: Bearer $POPNOW_API_KEY"Replace the prompt and any links with your own. The API tab has the response, polling and callback reference.
FLUX.2 Klein 9B LoRA API questions
How much does the FLUX.2 Klein 9B LoRA API cost?
FLUX.2 Klein 9B LoRA starts at 4 credits ($0.04) per image with Edit Image, its cheapest task. Credits are the same as on the website (1 credit = $0.01), new accounts get 30 free credits, and failed tasks are refunded.
What is the model name for FLUX.2 Klein 9B LoRA in the API?
Put black-forest-labs/flux-2-klein-9b-lora/text-to-image for Create Image; black-forest-labs/flux-2-klein-9b-lora/edit for Edit Image in the model field of POST /jobs/createTask.
Should I use this or FLUX.2 Klein Base 9B LoRA?
This is the step-distilled build: renders in about ten seconds and holds a polished, photographic look. Base is the undistilled build its makers recommend for training; it took two to five times longer in our tests and gave softer, more varied pictures. The same LoRAs load on both, so you can train on Base and run here.
My LoRA loaded but nothing changed. Why?
Three causes in our tests: the file was trained for another model (FLUX.1 or klein 4B), it was saved in diffusers PEFT format (keys ending in .default.weight), or it is a style LoRA whose look the prompt already asks for. None of these raise an error. Compare the same seed with and without the file.
What are the limits of the FLUX.2 Klein 9B LoRA API?
Resolutions: 1K · 2K; Aspect ratios: auto · 1:1 · 16:9 · 9:16 · 4:3 · 3:4 +4; Reference images: 3; Prompt length (characters): 5,000; Largest upload: 10 MB. Requests outside these limits are rejected before anything is charged.
Can I try FLUX.2 Klein 9B LoRA without writing code?
Yes. The Playground runs FLUX.2 Klein 9B LoRA on your PopNow credits, needs no API key, and shows the matching code for every run.
All FLUX models
FLUX.2 Klein Base 9B LoRA is the undistilled build: two to five times slower, with softer, more varied pictures. The distilled build is quicker and more polished.
- FLUX.2 Max APITop-tier FLUX: photoreal light and exact brand colorsFrom 11 credits per image
- FLUX 3 APIVideo with synced sound and a quick draft tierFrom 45 credits for a 5-second clip
- FLUX.2 Klein 9B LoRA APIFast FLUX.2 Klein 9B that loads up to three of your LoRAsFrom 3 credits per image
- FLUX.2 Klein Base 9B LoRA APIUndistilled Klein 9B for varied looks with your LoRAsFrom 4 credits per image
- FLUX.2 Klein 4B LoRA APISmall, quick FLUX.2 Klein 4B with your own LoRAsFrom 3 credits per image
- FLUX.2 Klein Base 4B LoRA APIUndistilled Klein 4B that loads your own LoRAsFrom 3 credits per image
- FLUX.2 Klein 9B APIFast FLUX edits that keep faces and poses intactFrom 2 credits per image
- FLUX.2 Klein 4B APIThe smallest, quickest FLUX for rapid draftsFrom 2 credits per image
- FLUX.2 Dev LoRA APIFLUX.2 Dev images and edits with your own LoRAsFrom 4 credits per image
- FLUX.2 Pro APIPhotoreal images with readable text and hex color controlFrom 5 credits per image
- FLUX.2 Flex APISpells headlines and labels exactly as writtenFrom 9 credits per image
- FLUX.2 Dev APIOpen-weights FLUX that can merge people into one sceneFrom 2 credits per image
- FLUX.1 Krea Dev LoRA APIPhotographic FLUX.1 Krea with your own LoRAsFrom 4 credits per image
- FLUX.1 Dev ControlNet LoRA APIPose, depth or edge control on FLUX.1 with your LoRAsFrom 6 credits per image
- FLUX.1 Fill Dev LoRA APIMasked inpainting on FLUX.1 Fill with your own LoRAsFrom 7 credits per image
- FLUX.1 Dev LoRA APIClassic FLUX.1 Dev with up to three of your LoRAsFrom 3 credits per image
- FLUX.1 Schnell LoRA APIFast FLUX.1 Schnell that loads your own LoRAsFrom 1 credit per image


