black-forest-labs/flux-2-klein-4b-lora/editFrom 4 credits per image· Edit Image

FLUX.2 Klein 4B LoRA image edit on Black Forest Labs' FLUX.2 [klein] 4B: change or combine up to three source images with a written instruction and up to three of your own LoRA files.

Call it with the model name black-forest-labs/flux-2-klein-4b-lora/edit on POST /jobs/createTask, from 4 credits per image ($0.04). New accounts get 30 free credits to try it in the Playground first.

  • Create Image
  • Edit Image
  • Up to 2K
  • Up to 3 reference images
  • 9 aspect ratios
  • Loads your own LoRA

Introduction

FLUX.2 Klein 4B LoRA Image edit changes or combines up to three source images with a written instruction on Black Forest Labs' FLUX.2 [klein] 4B, with up to three of your own LoRA files loaded. Keep the shape of your first image with auto, or choose one of nine ratios and a 1k or 2k size tier.

Choose a mode by starting material

What you haveMode
one to three pictures to change or combineFLUX.2 Klein 4B LoRA Image edit
a written description onlyFLUX.2 Klein 4B LoRA Text to image

Key features

Edits that follow the instruction

Change light, clothes or setting and keep faces and pose. In our tests the distilled build followed our edit instructions closely, including taking the clothes off a clothed photo.

Restyle with a LoRA

Load a style LoRA and ask for a redraw: a diner photo came back as a colored-pencil drawing with the woman and her dress kept.

Up to three sources

Combine a portrait with an outfit or a location. Name the sources as image 1, image 2 and image 3; faces can drift a little when you combine them.

Request parameters

ParameterRequiredDescription
aspect_ratioNoThe 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_urlsYesPhotos to edit or combine. Say in the prompt what each one adds.
lorasNoLoad your own LoRA files to lock in a style or character. Default: []
promptYesSay what to change and what must stay the same. Put a LoRA trigger phrase first.
resolutionNoOutput size. Bigger sizes look sharper and cost more. 1k · 2k · Default: 1k
seedNoReuse 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.

OptionCredits per image≈ USD
Standard3.06$0.031

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

Outfit and setting swaps

Put a person from one photo into a dress from another and a new place, in one request. Name the portrait as image 1 and the outfit as image 2, and say where the scene happens.

Reframing and relighting

Pick a wider ratio than the source and describe what should fill the new space, or keep auto and move a daytime photo to blue hour with one sentence about the light.

Prompt guide & pro tips

Protect first, change second

Open with what must stay (face, hair, pose), then describe the change. Short, concrete instructions work best.

Use auto to keep the shape

Auto keeps the first source's shape at about one megapixel. Choose a ratio only when you want the frame recomposed.

Compare against no LoRA

Run the same prompt and seed without the LoRA. If the two results look the same, the file was made for another base model, such as FLUX.1 or the 9B Klein models: those load without an error and do nothing here.

Use direct, public links

The link must download the .safetensors file itself.

API quick start

Call the FLUX.2 Klein 4B LoRA API in three steps

  1. 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.
  2. Send the request. POST /jobs/createTask with model black-forest-labs/flux-2-klein-4b-lora/edit and an input object that follows the parameter table. The response returns a task ID straight away.
  3. 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-4b-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 4B LoRA API questions

How much does the FLUX.2 Klein 4B LoRA API cost?

FLUX.2 Klein 4B 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 4B LoRA in the API?

Put black-forest-labs/flux-2-klein-4b-lora/text-to-image for Create Image; black-forest-labs/flux-2-klein-4b-lora/edit for Edit Image in the model field of POST /jobs/createTask.

What is the difference from FLUX.2 Klein Base 4B LoRA?

Both run Black Forest Labs' 4B Klein model. This one is the distilled build, made to finish in a few steps: in our tests it was about four times faster and followed edit instructions more reliably. Base 4B is the undistilled build its makers recommend for training; it is slower, gives more varied results and shows style LoRAs more strongly.

Which LoRAs work here?

Files trained for FLUX.2 [klein] 4B or Klein Base 4B. LoRAs from both builds loaded in our tests. LoRAs for FLUX.1 or the 9B Klein models load silently and have no effect.

My LoRA loaded but nothing changed. Why?

It was probably trained for another base model, or it needs its trigger phrase. Check the LoRA page for the trigger and put it first. Style LoRAs can also be faint on this distilled build; try a scale of 1.5 to 2.

What are the limits of the FLUX.2 Klein 4B 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 4B LoRA without writing code?

Yes. The Playground runs FLUX.2 Klein 4B LoRA on your PopNow credits, needs no API key, and shows the matching code for every run.

All FLUX models

FLUX.2 Klein Base 4B LoRA responds more strongly to style LoRAs and varies more between seeds, but is about four times slower.

More about FLUX.2 Klein 4B LoRA