Skip to content

Finegrain Eraser Bbox

Integrate

Model id finegrain-eraser/bbox
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/finegrain-eraser/bbox?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "box_prompts": [
      {
        "x_max": 0,
        "x_min": 0,
        "y_max": 0,
        "y_min": 0
      }
    ]
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

This request: $0.18 180 API credits Run it on this page

Get API key
Finegrain Image Editing #utility#editing

Erases the object inside a single bounding box you supply, with express, standard or premium modes

Finegrain · Image

Your first result goes here

Build a request below and run it with your API key. Outputs are copied to our storage, kept forever or 7 days for free.

Build a request

Controls are generated from the model schema. The code and the price update as you change them.

•required image_url
Drop a file, or

URL pointing to the image for editing.

mode default standard

Quality setting for erasure.

•required

Erasure region specified as a list of coordinates for the single supported bounding box prompt.

Advanced seed

Seed controlling randomness to make generation reproducible.

POST /run/finegrain-eraser/bbox?wait=20 quote → $0.18
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/finegrain-eraser/bbox?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "box_prompts": [
      {
        "x_max": 0,
        "x_min": 0,
        "y_max": 0,
        "y_min": 0
      }
    ]
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Run this request

Your key stays in this browser: it is sent only to the Doitong API and saved (localStorage) only if you tick Remember. Get an API key

About Finegrain Eraser Bbox

Takes an image and a bounding box in `box_prompts` and removes the object inside it, then reconstructs the background. Only one box is supported per request. `mode` can be express, standard (default) or premium, and `seed` ranges from 0 to 999 for reproducible output.

Parameters

Send either the canonical name or the native name, not both. Canonical names

NameType DefaultAllowed Description
image_urlrequired image
Typeurl · image
URL pointing to the image for editing.
box_promptsrequired
Typeobject[]
Erasure region specified as a list of coordinates for the single supported bounding box prompt.
box_prompts[].x_minoptional
Typeinteger
Default0
Minimum x-coordinate for the box.
box_prompts[].y_minoptional
Typeinteger
Default0
Minimum y-coordinate for the box.
box_prompts[].x_maxoptional
Typeinteger
Default0
Maximum x-coordinate for the prompt.
box_prompts[].y_maxoptional
Typeinteger
Default0
Maximum y-coordinate for the prompt.
modeoptional
Typeenum
Defaultstandard
expressstandardpremium
Quality setting for erasure.
seedoptional
Typeinteger | null
0 – 999
Seed controlling randomness to make generation reproducible.
required Canonical name, also accepted

File parameters take a public https:// URL, a data: URI up to 10 MB, or the file_url of an upload. Files

Output

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "finegrain-eraser/bbox",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 180,
    "usd": "0.18",
    "charged": 180,
    "refunded": 0
  },
  "input": {
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "box_prompts": [
      {
        "x_max": 0,
        "x_min": 0,
        "y_max": 0,
        "y_min": 0
      }
    ]
  },
  "output": {
    "image": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    },
    "used_seed": 1
  },
  "outputs": [
    {
      "type": "image",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "width": 1024,
      "height": 768,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
Your files, your choiceEvery outputs[].url is a copy on our storage: kept forever (paid per GB-month) or 7 days for free, by your account setting or ?storage=.
Same shape on every modeltype, url, content_type, width, height and duration, for images, video and audio alike. output is the model’s own result object.
Fields of output
image
object {url, content_type, file_name, file_size}Resulting image after the specified content has been removed.
used_seed
integerSeed value used during generation.

More models: Image Editing

For AI agents: this page as Markdown is at https://doitong.com/developers/models/finegrain-eraser/bbox.md. All models and guides: https://doitong.com/developers/llms.txt