Introducing the official FLUX MCP • Try now
curl --request POST \
--url https://api.bfl.ai/v1/flux-tools/erase-v1 \
--header 'Content-Type: application/json' \
--header 'x-key: <api-key>' \
--data '
{
"image": "<string>",
"mask": "<string>",
"dilate_pixels": 10,
"seed": 42,
"safety_tolerance": 2,
"output_format": "png",
"webhook_url": "<string>",
"webhook_secret": "<string>"
}
'{
"id": "<string>",
"polling_url": "<string>",
"cost": 123,
"input_mp": 123,
"output_mp": 123
}Submits an erase task using an input image and a mask identifying the object or region to remove.
curl --request POST \
--url https://api.bfl.ai/v1/flux-tools/erase-v1 \
--header 'Content-Type: application/json' \
--header 'x-key: <api-key>' \
--data '
{
"image": "<string>",
"mask": "<string>",
"dilate_pixels": 10,
"seed": 42,
"safety_tolerance": 2,
"output_format": "png",
"webhook_url": "<string>",
"webhook_secret": "<string>"
}
'{
"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.
Input model for public FLUX.2 erase.
Base64-encoded input image.
Base64-encoded black/white mask. White pixels indicate the object to remove; black pixels are preserved. Must have the same dimensions as the input image.
Number of pixels to dilate the mask by before removal. Dilation helps cover object edges.
0 <= x <= 100Optional seed for reproducibility.
42
Tolerance level for input and output moderation. Between 0 and 5, 0 being most strict, 5 being least strict.
0 <= x <= 52
jpeg, png, webp URL to receive webhook notifications
1 - 2083Optional secret for webhook signature verification
Was this page helpful?