Skip to main content
POST
/
v1
/
flux-tools
/
outpainting-v1
Outpaint or extend an image
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,
  "safety_tolerance": 2,
  "output_format": "png",
  "prompt": "<string>",
  "reference_offset_x": 123,
  "reference_offset_y": 123,
  "mode": "high"
}
'
{
  "id": "<string>",
  "polling_url": "<string>",
  "cost": 123,
  "input_mp": 123,
  "output_mp": 123
}

Authorizations

​
x-key
string
header
required

Body

application/json

Public contract for /v1/flux-tools/outpainting-v1.

​
input_image
string
required

Base64-encoded input (reference) image or HTTP(S) image URL.

​
width
integer
required

Target output width.

Required range: x >= 64
​
height
integer
required

Target output height.

Required range: x >= 64
​
auto_crop
boolean
default:false

If True, crop the input image to the canvas bounds when it extends beyond the edges. If False, an error is raised instead.

​
safety_tolerance
integer
default:2

Tolerance level for input and output moderation. Between 0 and 5, 0 being most strict, 5 being least strict. If you wish to increase the safety_tolerance beyond these levels please reach out to the team.

Required range: 0 <= x <= 5
​
output_format
enum<string> | null
default:png
Available options:
jpeg,
png,
webp
​
prompt
string | null

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.

​
reference_offset_x
integer | null

Left offset (px) of the reference image's top-left corner on the output canvas. Negative values are allowed. None = center horizontally.

​
reference_offset_y
integer | null

Top offset (px) of the reference image's top-left corner on the output canvas. Negative values are allowed. None = center vertically.

​
mode
enum<string>
default:high

Quality/speed trade-off. 'high' (default): highest-fidelity results, recommended whenever fine detail, prompt adherence, or consistency with complex content in the source image matters; slower. 'fast': significantly faster and well-suited for naturally extending most scenes (landscapes, backgrounds, textures, products); may produce lower fidelity in the extended region than 'high'.

Available options:
high,
fast

Response

Successful Response

​
id
string
required
​
polling_url
string
required
​
cost
number | null

Cost in credits for this request

​
input_mp
number | null

Input megapixels (2 decimal places)

​
output_mp
number | null

Output megapixels (2 decimal places)