GET

/v1/schemas/bfl/image/v1/flux-pro-1.0-fill-finetuned

Accept:

kind inputactivity imagehash 5af88e86…extracted Sep 11, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `bfcfd689618a9a8bd4a9824449dadf2dfdbce0a3c601a4ff9c33901da415fca1` { "fetchedAt": 1789104612, "extractorVersion": "1", "verifiedAt": null }

Request body

14 properties · 2 required · 1 $defs

property	type	description	constraints
finetune_id*	string	Name of the LoRA to use. For LoRAs from other organizations (public or shared), use the format 'org-id/lora-name'.
image*	string	A Base64-encoded string representing the image you wish to modify. Can contain alpha mask if desired.
user	string	Opaque identifier for the end user supplied by the calling platform.	length ≥ 1 · length ≤ 256 · nullable
finetune_strength	number	Strength of the fine-tuned model. 0.0 means no influence, 1.0 means full influence. Allowed values up to 2.0	0 ≤ n ≤ 2 · default: 1.1
mask	string	A Base64-encoded string representing a mask for the areas you want to modify in the image. The mask should be the same dimensions as the image and in black and white. Black areas (0%) indicate no modification, while white areas (100%) specify areas for inpainting. Optional if you provide an alpha mask in the original image. Validation: The endpoint verifies that the dimensions of the mask match the original image.	nullable
prompt	string	The description of the changes you want to make. This text guides the inpainting process, allowing you to specify features, styles, or modifications for the masked area.	default: ""
steps	integer	Number of steps for the image generation process	15 ≤ n ≤ 50 · default: 50
prompt_upsampling	boolean	Whether to perform upsampling on the prompt. If active, automatically modifies the prompt for more creative generation	default: false
seed	integer	Optional seed for reproducibility	nullable
guidance	number	Guidance strength for the image generation process	1.5 ≤ n ≤ 100 · default: 60
output_format	enum	Output format for the generated image. Can be 'jpeg', 'png', or 'webp'.	jpeg \| png \| webp · nullable
safety_tolerance	integer	Tolerance level for input and output moderation. Between 0 and 6, 0 being most strict, 6 being least strict.	0 ≤ n ≤ 6 · default: 2
webhook_url	string	URL to receive webhook notifications	length ≥ 1 · length ≤ 2083 · format: uri · nullable
webhook_secret	string	Optional secret for webhook signature verification	nullable

Types

1 $defs

OutputFormatenum

jpeg | png | webp

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"bfl","endpointId":"v1/flux-pro-1.0-fill-finetuned","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}