Introducing the official FLUX MCP • Try now
FLUX.2 Models
FLUX.2 Klein Models
Legacy Models
- POSTCreate an image with FLUX.1 Kontext [pro] (legacy, use FLUX.2 [PRO] for editing)
- POSTCreate an image with FLUX.1 Kontext [max] (legacy, use FLUX.2 [PRO] for editing)
- POSTGenerate an image with FLUX 1.1 [pro].
- POSTGenerate an image with FLUX 1.1 [pro] with ultra mode and optional raw mode.
- POSTGenerate an image with FLUX.1 [dev].
- POSTGenerate an image with FLUX.1 Fill [pro] using an input image and mask.
- POSTExpand an image by adding pixels on any side.
Fine-tuning
Licensing
curl --request POST \
--url https://api.bfl.ai/v1/flux-tools/outpainting-v1 \
--header 'Content-Type: application/json' \
--header 'x-key: <api-key>' \
--data '
{
"input_image": "<string>",
"width": 65,
"height": 65,
"auto_crop": false,
"output_format": "png",
"prompt": "<string>",
"reference_offset_x": 123,
"reference_offset_y": 123
}
'{
"id": "<string>",
"polling_url": "<string>",
"cost": 123,
"input_mp": 123,
"output_mp": 123
}Outpaint or extend an image
Submits an outpainting task. The input image is placed on a (width, height) canvas at the given offset, and the surrounding region is generated by a FLUX outpainting model.
curl --request POST \
--url https://api.bfl.ai/v1/flux-tools/outpainting-v1 \
--header 'Content-Type: application/json' \
--header 'x-key: <api-key>' \
--data '
{
"input_image": "<string>",
"width": 65,
"height": 65,
"auto_crop": false,
"output_format": "png",
"prompt": "<string>",
"reference_offset_x": 123,
"reference_offset_y": 123
}
'{
"id": "<string>",
"polling_url": "<string>",
"cost": 123,
"input_mp": 123,
"output_mp": 123
}Documentation Index
Fetch the complete documentation index at: https://docs.bfl.ml/llms.txt
Use this file to discover all available pages before exploring further.
Authorizations
Body
Public contract for /v1/flux-tools/outpainting-v1.
Base64-encoded input (reference) image.
Target output width.
x >= 64Target output height.
x >= 64If True, crop the input image to the canvas bounds when it extends beyond the edges. If False, an error is raised instead.
jpeg, png, webp Experimental: optional text guidance for the outpainted region. The model may not strictly follow this prompt; the visual content of the input image is the primary signal. Leave unset for default behavior.
Left offset (px) of the reference image's top-left corner on the output canvas. Negative values are allowed. None = center horizontally.
Top offset (px) of the reference image's top-left corner on the output canvas. Negative values are allowed. None = center vertically.
Was this page helpful?