black-forest-labs/flux-2-klein-base-9b-lora/editFrom 5 credits per image· Edit Image

FLUX.2 Klein Base 9B LoRA runs Black Forest Labs' undistilled FLUX.2 [klein] Base 9B with up to three of your own LoRA files per request. Base is the build its makers recommend for fine-tuning and LoRA training: slower than the distilled klein 9B, with softer, more varied pictures.

Call it with the model name black-forest-labs/flux-2-klein-base-9b-lora/edit on POST /jobs/createTask, from 5 credits per image ($0.05). 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 Base 9B LoRA Image editing changes one to three source images from a written instruction on Black Forest Labs' undistilled FLUX.2 [klein] Base 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. Edits took about half a minute at 1k in our tests, and nothing is filtered.

Choose a mode by starting material

What you haveMode
a written description and a LoRAFLUX.2 Klein Base 9B LoRA Text to image
one to three images to changeFLUX.2 Klein Base 9B LoRA Image editing

Key features

Same person, new place

An office portrait became a linen shirt and a watering can in a fern house, silver hair and stubble intact.

LoRAs on real photos

A film-still or analog LoRA sets the grade of an edit.

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
Standard4.68$0.047

Each task is rounded up to whole credits, so one run at the lowest tier costs 5 credits per image ($0.05).

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

Use cases

Testing a LoRA on real photos

See how a LoRA you trained on Base treats real people and places, with their faces, before you build a series on it.

Wardrobe and location changes

Change outfit and setting in one pass while keeping the person, for lookbooks, mood boards and character references.

Prompt guide & pro tips

Protect first, then change

Name what must stay, such as face, hair, expression and pose, then the change: garment, place and light. Short, concrete instructions work best, and the result keeps the first source's shape unless you pick a ratio.

Watch strong LoRAs

An anatomy LoRA at scale 1 replaced the framing and the person in one of our tests. Start around 0.6 on edits and raise it only while the face still matches the source.

Expect about half a minute

Edits took about 30 seconds at 1k and close to a minute at 2k in our tests. Work at 1k with auto while you settle the instruction, then pick a ratio and 2k for the final.

API quick start

Call the FLUX.2 Klein Base 9B 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-base-9b-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-base-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 Base 9B LoRA API questions

How much does the FLUX.2 Klein Base 9B LoRA API cost?

FLUX.2 Klein Base 9B LoRA starts at 5 credits ($0.05) 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 Base 9B LoRA in the API?

Put black-forest-labs/flux-2-klein-base-9b-lora/text-to-image for Create Image; black-forest-labs/flux-2-klein-base-9b-lora/edit for Edit Image in the model field of POST /jobs/createTask.

How is Base different from the distilled klein 9B?

Black Forest Labs step- and guidance-distilled klein 9B to run in four steps. Base is the same 9B model without that distillation: its makers describe it as having higher output diversity and recommend it for fine-tuning and LoRA training. Here it took two to five times longer per image, gave softer, more film-like pictures. Their reference settings run Base at 50 steps against four for the distilled build.

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.

Should I use this or FLUX.2 Klein 9B LoRA?

Use Base to check a LoRA you trained on Base, or for a softer, more varied look. Use the distilled build when speed matters: it renders in about ten seconds and gives a more polished photographic finish.

What are the limits of the FLUX.2 Klein Base 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 Base 9B LoRA without writing code?

Yes. The Playground runs FLUX.2 Klein Base 9B LoRA on your PopNow credits, needs no API key, and shows the matching code for every run.

All FLUX models

FLUX.2 Klein 9B LoRA renders in about ten seconds with a more polished photographic finish.

More about FLUX.2 Klein Base 9B LoRA