Grok Imagine Image · Edit
Integrar
xai/grok-imagine-image/edit
# 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/xai/grok-imagine-image/edit?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}'
# 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 $DOITONG_API_KEY"
const API = "https://api.doitong.com/v1";
const headers = {
"Authorization": "Bearer " + process.env.DOITONG_API_KEY,
"Content-Type": "application/json",
};
// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/xai/grok-imagine-image/edit?wait=20", {
method: "POST",
headers,
body: JSON.stringify({
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);
// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
import os
import requests
API = "https://api.doitong.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}
payload = {
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
}
# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/xai/grok-imagine-image/edit", 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/pt-BR/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": "xai/grok-imagine-image/edit",
"input": {
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}
}
Chame o modelo Grok Imagine Image · Edit (xai/grok-imagine-image/edit) por meio da Doitong API. Documentação para agentes: https://doitong.com/pt-BR/developers/models/xai/grok-imagine-image/edit.md
POST https://api.doitong.com/v1/run/xai/grok-imagine-image/edit?wait=20
Authorization: Bearer $DOITONG_API_KEY
Content-Type: application/json
{
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}
Se o status da resposta for "queued" ou "running", consulte GET https://api.doitong.com/v1/requests/REQUEST_ID?wait=20 repetidamente até que seja "succeeded"; os arquivos estão em outputs[].url. POST https://api.doitong.com/v1/quote/xai/grok-imagine-image/edit com o mesmo corpo retorna o preço exato antes da execução.
Esta solicitação: $ 0,022 22 créditos de API Executar nesta página
Sua nova chave de API. Ela é exibida apenas agora e já está no código e no campo de chave de API abaixo. Mantenha-a em segredo: nunca a coloque em um código executado no navegador.
Feito no Doitong
Trabalhos públicos feitos com Grok Imagine Image pela comunidade Doitong. Reutilize um prompt com um clique.
Art style: Professional portrait photography, cinematic lighting, realistic high detail. День. Тротуар у фудтрака, точно восемь горожан стоят в очереди неподвижно. Медиум: клерк в расстёгнутом пальто держит сэндвич в правой руке у рта. ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ FINAL STYLE...
Art style: Professional portrait photography, cinematic lighting, realistic high detail. День, медиум изнутри окна фудтрака. Арина за стойкой держит в правой руке золотой конверт, в левой магнит. ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ FINAL STYLE ENFORCEMENT (this is the authoritative rendering...
Art style: Professional portrait photography, cinematic lighting, realistic high detail. Арена, свет софитов, на табло алые цифры 00:45. Трибуны полны и неподвижны. Медиум: Арина с чёрной повязкой на волосах держит сковороду правой рукой. Натан стоит за столом напротив, в его руке пинцет....
Art style: Professional portrait photography, cinematic lighting, realistic high detail. Медиум: Арина у стола арены, в правой руке сковорода над пустой глиняной тарелкой, свет софитов. ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ FINAL STYLE ENFORCEMENT (this is the authoritative rendering directive —...
Art style: Professional portrait photography, cinematic lighting, realistic high detail. Судейский стол под софитами. Точно трое критиков в смокингах сидят за ним. Перед ними тарелка с пеной и глиняная тарелка с глазурью. ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ FINAL STYLE ENFORCEMENT (this is the...
Art style: Professional portrait photography, cinematic lighting, realistic high detail. Арена, медиум: Натан у стального стола держит пинцет в правой руке, за ним тёмный медиафасад. ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ FINAL STYLE ENFORCEMENT (this is the authoritative rendering directive — it...
Art style: Professional portrait photography, cinematic lighting, realistic high detail. Медиум: Арина у стола арены держит обеими руками золотой кубок на уровне груди, золотой свет софитов. ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ FINAL STYLE ENFORCEMENT (this is the authoritative rendering...
Art style: Professional portrait photography, cinematic lighting, realistic high detail. День, светлая панорамная кухня с окнами. Медиум: Арина в чёрном кителе идёт к раздаче, в правой руке дымящееся блюдо. ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ FINAL STYLE ENFORCEMENT (this is the authoritative...
Art style: 3D Cartoon. Opa Sigmund. Ein 70-jähriger Mann mit flauschigem weißem Haar, einem gepflegten weißen Bart und einer runden Brille auf einer freundlich faltigen Nase. Er trägt einen kuscheligen braunen Strick-Cardigan über einem weißen Hemd mit dunkler Fliege. Seine Augen sind ein warmes...
Art style: 3D Cartoon. Der Enkel. Ein sechsjähriger Junge mit zerzaustem dunkelbraunem Haar und großen, neugierigen braunen Augen. Er trägt einen groben Wollpullover in Waldgrün. Er sitzt mit verschränkten Beinen auf einem gemusterten Orientteppich und blickt mit offenem Mund und voller...
Art style: 3D Cartoon. Columbus standing in the middle ground. Columbus is standing on deck in the middle ground in the midground. Torso facing camera. Head facing camera. Eyes on horizon. Gripping railing. Determined. Ships sits in the middle ground in the background. Wide shot from a low angle,...
Art style: 3D Cartoon. Sigmund standing in the near foreground; Enkel standing further back in the frame. Sigmund is standing on floor in the near foreground in the midground. Torso in three-quarter turn to screen-right. Head in three-quarter turn to screen-right. Eyes on Globe. On globe. Serene....
Art style: 3D Cartoon. Rodrigo standing in the middle ground. Rodrigo is standing on crow's nest in the middle ground in the foreground. Torso facing camera. Ships sits in the middle ground in the midground. Extreme wide shot from a high angle, 9:16. Horizon high. Opening extreme wide, ending...
Art style: Classic Fairytale. Бао. Round chubby plush panda toy, soft black-and-white fur with visible fabric pile texture, big fat white belly, black ear and limb patches, shiny black button eyes, tiny stitched smile, stubby legs, waddling gait, no clothing and no props. Silhouette tag: widest...
Cinematic head-and-shoulders portrait, face close-up, sharp eyes in crisp focus, shallow depth of field, soft key light with gentle rim light, filmic colour grading. The character looks slightly past the camera with a natural, expressive gaze. Neutral, softly blurred background. No text, no...
Art style: Paper Cut. PUP. Paper-cut style small sandy-brown puppy, fluffy layered paper fur, oversized paws and ears, bright shiny dark eyes, no grey on muzzle, the same frayed red collar with round brass tag but loose and sliding over one shoulder, textured torn paper edges, brighter warmer...
Criar uma solicitação
Os controles são gerados a partir do esquema do modelo. O código e o preço são atualizados conforme você os altera.
/run/xai/grok-imagine-image/edit?wait=20
cotação → $ 0,022
# 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/xai/grok-imagine-image/edit?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}'
# 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 $DOITONG_API_KEY"
const API = "https://api.doitong.com/v1";
const headers = {
"Authorization": "Bearer " + process.env.DOITONG_API_KEY,
"Content-Type": "application/json",
};
// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/xai/grok-imagine-image/edit?wait=20", {
method: "POST",
headers,
body: JSON.stringify({
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);
// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
import os
import requests
API = "https://api.doitong.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}
payload = {
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
}
# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/xai/grok-imagine-image/edit", 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": "xai/grok-imagine-image/edit",
"input": {
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
},
"wait_seconds": 20
}
}
}
Executar esta solicitação
Sua chave permanece neste navegador: ela é enviada somente à Doitong API e salva (localStorage) apenas se você marcar Lembrar. Obter uma chave de API
Sobre Grok Imagine Image · Edit
Edita imagens descritas por um prompt de até 8000 caracteres, usando até 3 URLs em `image_urls`. `aspect_ratio` usa auto por padrão, mantendo a proporção da primeira imagem de entrada, ou pode ser definido explicitamente. A resolução é 1k ou 2k, com até 4 saídas em jpeg, png ou webp. Um prompt revisado é retornado.
Parâmetros
Envie o nome canônico ou o nome nativo, não ambos. Nomes canônicos
promptobrigatório
num_imagesopcional
num_outputs
aspect_ratioopcional
resolutionopcional
output_formatopcional
enable_safety_checkeropcional
image_urlsopcional
images
Os parâmetros de arquivo aceitam uma URL https:// pública, um URI data: de até 10 MB ou o file_url de um upload. Arquivos
Saída
{
"id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
"object": "request",
"model": "xai/grok-imagine-image/edit",
"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": 22,
"usd": "0.022",
"charged": 22,
"refunded": 0
},
"input": {
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
},
"output": {
"images": [
{
"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,
"width": 1024,
"height": 768
}
],
"revised_prompt": "string"
},
"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"
}
}
Campos da saída
- images
- array of object {url, content_type, file_name, file_size, width, height}URL que aponta para a imagem editada.
- revised_prompt
- string | nullPrompt aprimorado usado para geração de imagens.
Outras variantes de Grok Imagine Image
Mais modelos: Edição de imagem
Para agentes de IA: esta página em Markdown está em https://doitong.com/pt-BR/developers/models/xai/grok-imagine-image/edit.md. Todos os modelos e guias: https://doitong.com/developers/llms.txt






