Detail repair

Start a new job

POST
/detail-repair

Regenerate a masked logo/detail on an uploaded image, using user-uploaded reference shots as ground truth. Produces num_candidates variations, each a standard ImageResult shown in the Gallery.

Authorization

token_auth
headerAuthorizationBearer <token>

Token-based authentication using access tokens.

Request Body

application/json
  1. body
image*Image

UUID of the uploaded image to fix (the detail/logo lives here).

references?array<string>

UUIDs of reference images where the detail is clearly visible (ground truth). Optional — the lambda can fix some details from the prompt alone, but a reference makes the result far more accurate (and avoids hallucinating).

Itemsitems <= 10
mask?|

The marked region: {bbox_norm: [x, y, w, h], strokes: [...]} in 0..1 coords. Optional when mask_image is given (the API binary-mask path).

Defaultnull
mask_image?|

UUID of an uploaded binary mask image (white = the area to repair) at the image-to-fix resolution. Pixel-precise alternative to mask for API pipelines — no UI strokes needed. Resolved to its S3 key and forwarded to the engine, which derives both the region shape and its bounding box from it.

Defaultnull
project_id*Project Id

Project key where images are stored.

num_candidates?Num Candidates

How many variations to generate (1-4).

Default1
model?Model

Generation engine (auto | nano_banana_2 | nano_banana_pro | seedream | gpt_image).

Default"auto"
category?Category

Prompt family / issue category. logo (default) and text/artifact/... use the logo-optimized prompt; general switches to general-purpose inpainting (any masked edit — hairstyle, garment colour, object removal, ...) driven by reviewer_note, with references showing the desired result. Free-form.

Default"logo"
image_notes?array<string>

Optional brand/style hints forwarded to the prompt.

Default[]
reviewer_note?|

Optional targeted instruction (e.g. 'fix the first letter').

Defaultnull
add_ai_watermark?Add Ai Watermark

Bake an 'AI-generated' disclosure mark into each output (irreversible).

Defaultfalse
mode?Mode

Generation strategy (enterprise only). guided-blend = replace only the masked area and blend the seam (default); guided = redraw the whole crop; annotated / marked = single-image variants. Ignored for non-enterprise.

Default"guided-blend"
context_factor?|

How much surrounding image the model sees (enterprise only): crop side = context_factor × mask size. None → engine default. Ignored for non-enterprise.

Defaultnull

Response Body

Successful Response

application/json
  1. response
job_id*Job Id
status*Status
message*Message
curl -X POST "https://example.com/detail-repair" \  -H "Content-Type: application/json" \  -d '{    "image": "string",    "project_id": "string"  }'
{  "job_id": "string",  "status": "string",  "message": "string"}