FLUX 3 Klein Base LoRA API

About FLUX 3 Klein Base LoRA

FLUX 3 Klein Base that loads your own LoRAs.

Call it with the model name black-forest-labs/flux-3-klein-base-lora/edit on POST /jobs/createTask, from 9 credits per image ($0.09).

Introduction

FLUX 3 Klein Base LoRA Image editing changes or combines one to three source images from a written instruction on Black Forest Labs' FLUX 3 Image Klein Base, with up to three of your own LoRA files loaded. Refer to sources as image 1, image 2 and image 3, keep the first image's shape with auto or pick one of fifteen, and choose 1k or 2k. The model sometimes leaves clothing in place.

Choose a mode by starting material

Key features

Edit-trained LoRAs

LoRAs trained for editing on Klein Base change how the model edits. An outpainting LoRA, given a portrait padded with flat gray, filled the gray with the rest of a sauna changing room and kept the original picture where it was; without it, the same request redrew more of the scene.

Several sources with a LoRA

Combine up to three images and load LoRAs in the same request. Say what each source brings and put the LoRA's trigger or instruction first, so the model knows which part of the prompt belongs to the LoRA.

No review of LoRA files

LoRA files and results are not filtered.

Request parameters

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.

For an exact number before you run, send the same body to POST /jobs/quote.

Use cases

Outpainting and reframing

Pad a picture with gray to a wider or taller canvas and let an outpainting LoRA continue the scene, for banners and social formats cut from portrait photos.

Styling with references

Put a garment from a product photo on a person from another photo while a LoRA sets the look of the series.

Prompt guide & pro tips

Follow the LoRA card exactly

Edit LoRAs often expect a fixed instruction and a prepared input, such as flat #808080 gray padding for outpainting. Copy the instruction from the card to the start of the prompt and prepare the image the same way.

Choose the canvas shape

For outpainting, set the aspect ratio to the shape of the padded canvas, or leave auto so the first image decides. The model keeps that shape at the chosen size tier.

Compare with the same seed

Run the same edit with and without the LoRA. Edits are close but not always pixel-identical between runs, so look for a clear difference before you put it down to the LoRA.

API quick start

Call the FLUX 3 Klein Base 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-3-klein-base-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-3-klein-base-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",
    "output_format": "jpeg"
  }
}'

# 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 3 Klein Base LoRA API questions

More about FLUX 3 Klein Base LoRA

Try it

FLUX 3 Klein Base LoRA AI Image Generator onlineCreate images with FLUX 3 Klein Base LoRA in PopNow

Endpoints

FLUX 3 Klein Base LoRA · Create Image

Docs

FLUX 3 Klein Base LoRA model ID and input schema in the API docsPopNow API quickstart: your first request in five minutesImage generation guide for the PopNow APIWebhooks: get FLUX 3 Klein Base LoRA results without polling