Finegrain Eraser Bbox
Integra
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 $DOITONG_API_KEY"
const API = "https://api.doitong.com/v1";
const headers = {
"Authorization": "Bearer " + process.env.DOITONG_API_KEY,
"Content-Type": "application/json",
};
// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/finegrain-eraser/bbox?wait=20", {
method: "POST",
headers,
body: JSON.stringify({
"image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
"box_prompts": [
{
"x_max": 0,
"x_min": 0,
"y_max": 0,
"y_min": 0
}
]
}),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);
// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
import os
import requests
API = "https://api.doitong.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}
payload = {
"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,
},
],
}
# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/finegrain-eraser/bbox", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])
# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
# 1. Connect once (Claude Code; Cursor, VS Code, Claude Desktop: https://doitong.com/it/developers/docs/mcp)
claude mcp add --transport http doitong-models https://api.doitong.com/v1/mcp \
--header "Authorization: Bearer $DOITONG_API_KEY"
# 2. Your agent calls the "run" tool with:
{
"model_id": "finegrain-eraser/bbox",
"input": {
"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
}
]
}
}
Chiama il modello Finegrain Eraser Bbox (finegrain-eraser/bbox) tramite Doitong API. Documentazione per gli agenti: https://doitong.com/it/developers/models/finegrain-eraser/bbox.md
POST https://api.doitong.com/v1/run/finegrain-eraser/bbox?wait=20
Authorization: Bearer $DOITONG_API_KEY
Content-Type: application/json
{
"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
}
]
}
Se lo stato della risposta è "queued" o "running", interroga GET https://api.doitong.com/v1/requests/REQUEST_ID?wait=20 finché non diventa "succeeded"; i file si trovano in outputs[].url. POST https://api.doitong.com/v1/quote/finegrain-eraser/bbox con lo stesso body restituisce il prezzo esatto prima dell'esecuzione.
Questa richiesta: 0,18 $ 180 crediti API Esegui in questa pagina
La tua nuova chiave API. Viene mostrata solo ora ed è già presente nel codice e nel campo della chiave API qui sotto. Mantienila segreta: non inserirla mai nel codice eseguito in un browser.
Il tuo primo risultato apparirà qui
Crea una richiesta qui sotto ed eseguila con la tua chiave API. Gli output vengono copiati nella nostra archiviazione, conservati per sempre oppure 7 giorni gratuitamente.
Crea una richiesta
I controlli vengono generati dallo schema del modello. Il codice e il prezzo si aggiornano mentre li modifichi.
/run/finegrain-eraser/bbox?wait=20
preventivo → 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 $DOITONG_API_KEY"
const API = "https://api.doitong.com/v1";
const headers = {
"Authorization": "Bearer " + process.env.DOITONG_API_KEY,
"Content-Type": "application/json",
};
// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/finegrain-eraser/bbox?wait=20", {
method: "POST",
headers,
body: JSON.stringify({
"image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
"box_prompts": [
{
"x_max": 0,
"x_min": 0,
"y_max": 0,
"y_min": 0
}
]
}),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);
// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
import os
import requests
API = "https://api.doitong.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}
payload = {
"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,
},
],
}
# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/finegrain-eraser/bbox", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])
# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "run",
"arguments": {
"model_id": "finegrain-eraser/bbox",
"input": {
"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
}
]
},
"wait_seconds": 20
}
}
}
Esegui questa richiesta
La tua chiave rimane in questo browser: viene inviata solo al Doitong API e salvata in localStorage solo se selezioni Ricorda. Ottieni una chiave API
Informazioni su Finegrain Eraser Bbox
Riceve un'immagine e un riquadro di delimitazione in `box_prompts`, rimuove l'oggetto al suo interno e ricostruisce lo sfondo. È supportato un solo riquadro per richiesta. `mode` può essere express, standard (predefinito) o premium, mentre `seed` varia da 0 a 999 per ottenere risultati riproducibili.
Parametri
Invia il nome canonico oppure il nome nativo, non entrambi. Nomi canonici
image_urlobbligatorio
image
box_promptsobbligatorio
box_prompts[].x_minfacoltativo
box_prompts[].y_minfacoltativo
box_prompts[].x_maxfacoltativo
box_prompts[].y_maxfacoltativo
modefacoltativo
seedfacoltativo
I parametri file accettano un URL pubblico https://, un URI data: fino a 10 MB oppure il file_url di un caricamento. File
Output
{
"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"
}
}
Campi dell'output
- image
- object {url, content_type, file_name, file_size}Immagine risultante dopo la rimozione del contenuto specificato.
- used_seed
- integerValore seed usato durante la generazione.
Altre varianti di Finegrain Eraser
Altri modelli: Modifica immagini
Per gli agenti AI: questa pagina in Markdown è disponibile all'indirizzo https://doitong.com/it/developers/models/finegrain-eraser/bbox.md. Tutti i modelli e le guide: https://doitong.com/developers/llms.txt






