popnow
Sign inStart creating

black-forest-labs/flux-2-dev/editFrom 4 credits per image· Edit Image

FLUX.2 [dev] image editing from Black Forest Labs' open-weights model. It takes one to three source images and a prompt, keeps faces recognisable, and can combine people from separate photos into one scene.

Call it with the model name black-forest-labs/flux-2-dev/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
by Black Forest LabsGet API keyFLUX.2 Dev examples and prompts →

Introduction

FLUX.2 Dev Image Edit changes or combines up to three source images on Black Forest Labs' FLUX.2 [dev], a 32-billion-parameter open-weights model. Describe the new outfit, setting or light, name what must stay, and get one image back.

Choose a mode by starting material

What you haveMode
one to three images to change or combineFLUX.2 Dev Image Edit
a written brief onlyFLUX.2 Dev Text to image

Key features

Up to three references

List the images in the order your prompt mentions them and refer to them as image 1, image 2 and image 3. In our test a woman from one portrait and a man from another danced together in a new scene with both faces still close to their photos.

Framing that follows the source

With the shape on auto the result keeps the first image's proportions at about one megapixel. Pick a ratio and 2k when you want a different crop or more pixels.

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.
promptYesSay what to change and what must stay the same.
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
Standard3.47$0.035

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

A new outfit and setting for the same person

Move a person from an office to a bar or from a street to a beach, with another outfit and light, while the face stays.

Two people in one scene

Bring people from separate portraits into one frame for a couple shot or a character pair.

Relighting and colour changes

Ask for a new light source with a hex colour and keep the rest of the composition.

Prompt guide & pro tips

Say what stays

Start with "same man, same face and beard", then list what changes.

Number your people

When combining photos, write "the woman from image 1 and the man from image 2" and ask to keep both faces exactly as in the photos.

Keep one person per frame when it matters

Add "alone in the frame, no other people" to stop extra figures appearing in the background.

Start with auto

Leave the shape on auto first. Choose a ratio and 2k once you like the content, and keep the seed to compare the larger version.

Use clear sources

Well-lit, front-facing photos carry faces over best. The second and third people are a little less stable than the first.

API quick start

Call the FLUX.2 Dev 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-dev/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-dev/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 Dev API questions

How much does the FLUX.2 Dev API cost?

FLUX.2 Dev 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 Dev in the API?

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

Can it write text inside the image?

Yes, short text works well: in our tests quoted signs came back spelled as written. Put the exact words in quotation marks and say where they go. Long paragraphs may still contain mistakes.

Do hex colours work?

Yes, as a strong hint. A code such as #FF4F8B next to the neon sign tinted the room magenta. It is not an exact colour match.

How many reference images can I use?

One to three in Edit mode, in the order your prompt mentions them. Say "the woman from image 1" and "the man from image 2" when you combine people.

What are the limits of the FLUX.2 Dev 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 Dev without writing code?

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

All FLUX models

FLUX.2 Pro stays more consistent on text and faces; Dev is the open model of the family.

More about FLUX.2 Dev