Introduction
FLUX.2 [pro] Edit runs Black Forest Labs' FLUX.2 [pro] on images you already have. It accepts one to three sources, applies the change you describe, and returns 1k or 2k in the source shape or one of nine shapes.
Choose a mode by starting material
| What you have | Mode |
|---|---|
| a written brief | FLUX.2 [pro] Text to image |
| one to three images to change or combine | FLUX.2 [pro] Edit |
Key features & highlights
Multi-reference composites
Combine a person, a product and a place from separate photos. In our headphone ad the face, hair and cardigan and the headphones' design stayed as in the sources.
Scene and light changes
Swap the setting or relight a photo while the subject stays put. Our sunny street became a rainy neon night with raindrops on the blazer.
Text added in the edit
Add a headline to the picture in the same step. Ours was spelled as quoted.
Flat price per image
One source or three, 1k or 2k, an edit is the same price.
Strict on people
In our tests portrait sources were refused even for a Mild-level outfit change. Refused requests are not charged.
Request parameters
| Parameter | Required | Description |
|---|---|---|
prompt | Yes | Required, up to 5,000 characters. Say what to change and what must stay the same, and refer to sources as image 1, image 2 and image 3 in upload order. at least 1 characters · at most 5000 characters |
image_urls | Yes | Required, one to three source images, up to 10 MB each. Upload them in the order your prompt refers to them. at least 1 items · at most 3 items |
aspect_ratio | No | auto (default) keeps the shape of the first source image at about one megapixel; or pick one of nine shapes from 21:9 to 9:21. The shape does not change the price. |
resolution | No | 1k (default) or 2k. It applies only when you choose a shape; with auto the result stays at about one megapixel. |
seed | No | Optional whole number from 0 to 2147483647. Reuse it while changing the prompt to compare variations; it does not guarantee an identical image. |
Pricing
$0.058 / image
Billed as a flat price per image, whatever the number of sources or the size tier. Refused and failed requests are not charged.
Use cases
Advertisements from separate assets
Bring a model photo, a product shot and a location together into one visual.
Mood variations
Show the same scene by day, at night or in rain for a client choosing a direction.
Product and place restyling
Change the background, light or style of a product, a room or a portrait.
Prompt guide & pro tips
Number the sources
Say image 1 is the person, image 2 the product, image 3 the place, in upload order.
Name what must stay
After the change, list the face, outfit, pose or design that has to remain exactly as it was.
Change one thing at a time
A single clear change keeps the rest of the frame stable; chain edits instead of packing several into one.
Allow time
Edits took 45 to 120 seconds in our tests.
Keep it safe for work
This model is strict on people, so use it for products, places and portraits that stay safe for work.
API quick start
# Generate the idempotency key once; reuse it when retrying after a lost response.
export SPICY_IDEMPOTENCY_KEY="${SPICY_IDEMPOTENCY_KEY:-$(uuidgen)}"
curl -X POST https://api.spicyapi.ai/api/v1/jobs/createTask \
-H "Authorization: Bearer $SPICY_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $SPICY_IDEMPOTENCY_KEY" \
-d '{
"model": "black-forest-labs/flux-2-pro/edit",
"input": {
"aspect_ratio": "auto",
"image_urls": [
"https://example.com/reference.png"
],
"prompt": "A ceramic teapot on a linen cloth, soft window light, muted palette",
"resolution": "1k"
}
}'
# Copy data.taskId from the response into TASK_ID, then poll the status.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.spicyapi.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
-H "Authorization: Bearer $SPICY_API_KEY"
See the API reference for authentication, the complete schema, polling, and error handling.
























