curl --request POST \
--url https://api.apimart.ai/v1/images/generations \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"model": "gpt-image-1-official",
"prompt": "An ancient castle under a starry sky",
"size": "1:1",
"quality": "auto",
"n": 1
}'
import requests
url = "https://api.apimart.ai/v1/images/generations"
payload = {
"model": "gpt-image-1-official",
"prompt": "An ancient castle under a starry sky",
"size": "1:1",
"quality": "auto",
"n": 1
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.json())
const url = "https://api.apimart.ai/v1/images/generations";
const payload = {
model: "gpt-image-1-official",
prompt: "An ancient castle under a starry sky",
size: "1:1",
quality: "auto",
n: 1,
};
const headers = {
Authorization: "Bearer <token>",
"Content-Type": "application/json",
};
fetch(url, {
method: "POST",
headers: headers,
body: JSON.stringify(payload),
})
.then((response) => response.json())
.then((data) => console.log(data))
.catch((error) => console.error("Error:", error));
package main
import (
"bytes"
"encoding/json"
"fmt"
"io/ioutil"
"net/http"
)
func main() {
url := "https://api.apimart.ai/v1/images/generations"
payload := map[string]interface{}{
"model": "gpt-image-1-official",
"prompt": "An ancient castle under a starry sky",
"size": "1:1",
"quality": "auto",
"n": 1,
}
jsonData, _ := json.Marshal(payload)
req, _ := http.NewRequest("POST", url, bytes.NewBuffer(jsonData))
req.Header.Set("Authorization", "Bearer <token>")
req.Header.Set("Content-Type", "application/json")
client := &http.Client{}
resp, err := client.Do(req)
if err != nil {
panic(err)
}
defer resp.Body.Close()
body, _ := ioutil.ReadAll(resp.Body)
fmt.Println(string(body))
}
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;
import java.net.URI;
public class Main {
public static void main(String[] args) throws Exception {
String url = "https://api.apimart.ai/v1/images/generations";
String payload = """
{
"model": "gpt-image-1-official",
"prompt": "An ancient castle under a starry sky",
"size": "1:1",
"quality": "auto",
"n": 1
}
""";
HttpClient client = HttpClient.newHttpClient();
HttpRequest request = HttpRequest.newBuilder()
.uri(URI.create(url))
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.POST(HttpRequest.BodyPublishers.ofString(payload))
.build();
HttpResponse<String> response = client.send(request,
HttpResponse.BodyHandlers.ofString());
System.out.println(response.body());
}
}
<?php
$url = "https://api.apimart.ai/v1/images/generations";
$payload = [
"model" => "gpt-image-1-official",
"prompt" => "An ancient castle under a starry sky",
"size" => "1:1",
"quality" => "auto",
"n" => 1
];
$ch = curl_init($url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($payload));
curl_setopt($ch, CURLOPT_HTTPHEADER, [
"Authorization: Bearer <token>",
"Content-Type: application/json"
]);
$response = curl_exec($ch);
curl_close($ch);
echo $response;
?>
require 'net/http'
require 'json'
require 'uri'
url = URI("https://api.apimart.ai/v1/images/generations")
payload = {
model: "gpt-image-1-official",
prompt: "An ancient castle under a starry sky",
size: "1:1",
quality: "auto",
n: 1
}
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = "Bearer <token>"
request["Content-Type"] = "application/json"
request.body = payload.to_json
response = http.request(request)
puts response.body
import Foundation
let url = URL(string: "https://api.apimart.ai/v1/images/generations")!
let payload: [String: Any] = [
"model": "gpt-image-1-official",
"prompt": "An ancient castle under a starry sky",
"size": "1:1",
"quality": "auto",
"n": 1
]
var request = URLRequest(url: url)
request.httpMethod = "POST"
request.setValue("Bearer <token>", forHTTPHeaderField: "Authorization")
request.setValue("application/json", forHTTPHeaderField: "Content-Type")
request.httpBody = try? JSONSerialization.data(withJSONObject: payload)
let task = URLSession.shared.dataTask(with: request) { data, response, error in
if let error = error {
print("Error: \(error)")
return
}
if let data = data, let responseString = String(data: data, encoding: .utf8) {
print(responseString)
}
}
task.resume()
using System;
using System.Net.Http;
using System.Text;
using System.Threading.Tasks;
class Program
{
static async Task Main(string[] args)
{
var url = "https://api.apimart.ai/v1/images/generations";
var payload = @"{
""model"": ""gpt-image-1-official"",
""prompt"": ""An ancient castle under a starry sky"",
""size"": ""1:1"",
""quality"": ""auto"",
""n"": 1
}";
using var client = new HttpClient();
client.DefaultRequestHeaders.Add("Authorization", "Bearer <token>");
var content = new StringContent(payload, Encoding.UTF8, "application/json");
var response = await client.PostAsync(url, content);
var result = await response.Content.ReadAsStringAsync();
Console.WriteLine(result);
}
}
import 'dart:convert';
import 'package:http/http.dart' as http;
void main() async {
final url = Uri.parse('https://api.apimart.ai/v1/images/generations');
final payload = {
'model': 'gpt-image-1-official',
'prompt': 'An ancient castle under a starry sky',
'size': '1:1',
'quality': 'auto',
'n': 1,
};
final response = await http.post(
url,
headers: {
'Authorization': 'Bearer <token>',
'Content-Type': 'application/json',
},
body: jsonEncode(payload),
);
print(response.body);
}
library(httr)
library(jsonlite)
url <- "https://api.apimart.ai/v1/images/generations"
payload <- list(
model = "gpt-image-1-official",
prompt = "An ancient castle under a starry sky",
size = "1:1",
quality = "auto",
n = 1
)
response <- POST(
url,
add_headers(
Authorization = "Bearer <token>",
`Content-Type` = "application/json"
),
body = toJSON(payload, auto_unbox = TRUE),
encode = "raw"
)
cat(content(response, "text"))
{
"code": 200,
"data": [
{
"status": "submitted",
"task_id": "task_01KXXXXXXXXXXXXXXX"
}
]
}
{
"error": {
"code": 400,
"message": "Invalid request parameters",
"type": "invalid_request_error"
}
}
{
"error": {
"code": 401,
"message": "Authentication failed, please check your API key",
"type": "authentication_error"
}
}
{
"error": {
"code": 402,
"message": "Insufficient balance, please top up and try again",
"type": "payment_required"
}
}
{
"error": {
"code": 403,
"message": "Access forbidden, you do not have permission to access this resource",
"type": "permission_error"
}
}
{
"error": {
"code": 429,
"message": "Too many requests, please try again later",
"type": "rate_limit_error"
}
}
{
"error": {
"code": 500,
"message": "Internal server error, please try again later",
"type": "server_error"
}
}
{
"error": {
"code": 502,
"message": "Bad gateway, server temporarily unavailable",
"type": "bad_gateway"
}
}
GPT-Image(1/1.5)
Génération d'images GPT-Image(1/1.5)
- Mode de traitement asynchrone, renvoie un ID de tâche pour les requêtes ultérieures
- Prend en charge les modes de génération texte-vers-image, image-vers-image et inpainting
- Prend en charge les arrière-plans transparents, plusieurs formats de sortie et niveaux de qualité
- Génération jusqu’à 4 images par requête, avec jusqu’à 15 images de référence
POST
/
v1
/
images
/
generations
curl --request POST \
--url https://api.apimart.ai/v1/images/generations \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"model": "gpt-image-1-official",
"prompt": "An ancient castle under a starry sky",
"size": "1:1",
"quality": "auto",
"n": 1
}'
import requests
url = "https://api.apimart.ai/v1/images/generations"
payload = {
"model": "gpt-image-1-official",
"prompt": "An ancient castle under a starry sky",
"size": "1:1",
"quality": "auto",
"n": 1
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.json())
const url = "https://api.apimart.ai/v1/images/generations";
const payload = {
model: "gpt-image-1-official",
prompt: "An ancient castle under a starry sky",
size: "1:1",
quality: "auto",
n: 1,
};
const headers = {
Authorization: "Bearer <token>",
"Content-Type": "application/json",
};
fetch(url, {
method: "POST",
headers: headers,
body: JSON.stringify(payload),
})
.then((response) => response.json())
.then((data) => console.log(data))
.catch((error) => console.error("Error:", error));
package main
import (
"bytes"
"encoding/json"
"fmt"
"io/ioutil"
"net/http"
)
func main() {
url := "https://api.apimart.ai/v1/images/generations"
payload := map[string]interface{}{
"model": "gpt-image-1-official",
"prompt": "An ancient castle under a starry sky",
"size": "1:1",
"quality": "auto",
"n": 1,
}
jsonData, _ := json.Marshal(payload)
req, _ := http.NewRequest("POST", url, bytes.NewBuffer(jsonData))
req.Header.Set("Authorization", "Bearer <token>")
req.Header.Set("Content-Type", "application/json")
client := &http.Client{}
resp, err := client.Do(req)
if err != nil {
panic(err)
}
defer resp.Body.Close()
body, _ := ioutil.ReadAll(resp.Body)
fmt.Println(string(body))
}
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;
import java.net.URI;
public class Main {
public static void main(String[] args) throws Exception {
String url = "https://api.apimart.ai/v1/images/generations";
String payload = """
{
"model": "gpt-image-1-official",
"prompt": "An ancient castle under a starry sky",
"size": "1:1",
"quality": "auto",
"n": 1
}
""";
HttpClient client = HttpClient.newHttpClient();
HttpRequest request = HttpRequest.newBuilder()
.uri(URI.create(url))
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.POST(HttpRequest.BodyPublishers.ofString(payload))
.build();
HttpResponse<String> response = client.send(request,
HttpResponse.BodyHandlers.ofString());
System.out.println(response.body());
}
}
<?php
$url = "https://api.apimart.ai/v1/images/generations";
$payload = [
"model" => "gpt-image-1-official",
"prompt" => "An ancient castle under a starry sky",
"size" => "1:1",
"quality" => "auto",
"n" => 1
];
$ch = curl_init($url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($payload));
curl_setopt($ch, CURLOPT_HTTPHEADER, [
"Authorization: Bearer <token>",
"Content-Type: application/json"
]);
$response = curl_exec($ch);
curl_close($ch);
echo $response;
?>
require 'net/http'
require 'json'
require 'uri'
url = URI("https://api.apimart.ai/v1/images/generations")
payload = {
model: "gpt-image-1-official",
prompt: "An ancient castle under a starry sky",
size: "1:1",
quality: "auto",
n: 1
}
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = "Bearer <token>"
request["Content-Type"] = "application/json"
request.body = payload.to_json
response = http.request(request)
puts response.body
import Foundation
let url = URL(string: "https://api.apimart.ai/v1/images/generations")!
let payload: [String: Any] = [
"model": "gpt-image-1-official",
"prompt": "An ancient castle under a starry sky",
"size": "1:1",
"quality": "auto",
"n": 1
]
var request = URLRequest(url: url)
request.httpMethod = "POST"
request.setValue("Bearer <token>", forHTTPHeaderField: "Authorization")
request.setValue("application/json", forHTTPHeaderField: "Content-Type")
request.httpBody = try? JSONSerialization.data(withJSONObject: payload)
let task = URLSession.shared.dataTask(with: request) { data, response, error in
if let error = error {
print("Error: \(error)")
return
}
if let data = data, let responseString = String(data: data, encoding: .utf8) {
print(responseString)
}
}
task.resume()
using System;
using System.Net.Http;
using System.Text;
using System.Threading.Tasks;
class Program
{
static async Task Main(string[] args)
{
var url = "https://api.apimart.ai/v1/images/generations";
var payload = @"{
""model"": ""gpt-image-1-official"",
""prompt"": ""An ancient castle under a starry sky"",
""size"": ""1:1"",
""quality"": ""auto"",
""n"": 1
}";
using var client = new HttpClient();
client.DefaultRequestHeaders.Add("Authorization", "Bearer <token>");
var content = new StringContent(payload, Encoding.UTF8, "application/json");
var response = await client.PostAsync(url, content);
var result = await response.Content.ReadAsStringAsync();
Console.WriteLine(result);
}
}
import 'dart:convert';
import 'package:http/http.dart' as http;
void main() async {
final url = Uri.parse('https://api.apimart.ai/v1/images/generations');
final payload = {
'model': 'gpt-image-1-official',
'prompt': 'An ancient castle under a starry sky',
'size': '1:1',
'quality': 'auto',
'n': 1,
};
final response = await http.post(
url,
headers: {
'Authorization': 'Bearer <token>',
'Content-Type': 'application/json',
},
body: jsonEncode(payload),
);
print(response.body);
}
library(httr)
library(jsonlite)
url <- "https://api.apimart.ai/v1/images/generations"
payload <- list(
model = "gpt-image-1-official",
prompt = "An ancient castle under a starry sky",
size = "1:1",
quality = "auto",
n = 1
)
response <- POST(
url,
add_headers(
Authorization = "Bearer <token>",
`Content-Type` = "application/json"
),
body = toJSON(payload, auto_unbox = TRUE),
encode = "raw"
)
cat(content(response, "text"))
{
"code": 200,
"data": [
{
"status": "submitted",
"task_id": "task_01KXXXXXXXXXXXXXXX"
}
]
}
{
"error": {
"code": 400,
"message": "Invalid request parameters",
"type": "invalid_request_error"
}
}
{
"error": {
"code": 401,
"message": "Authentication failed, please check your API key",
"type": "authentication_error"
}
}
{
"error": {
"code": 402,
"message": "Insufficient balance, please top up and try again",
"type": "payment_required"
}
}
{
"error": {
"code": 403,
"message": "Access forbidden, you do not have permission to access this resource",
"type": "permission_error"
}
}
{
"error": {
"code": 429,
"message": "Too many requests, please try again later",
"type": "rate_limit_error"
}
}
{
"error": {
"code": 500,
"message": "Internal server error, please try again later",
"type": "server_error"
}
}
{
"error": {
"code": 502,
"message": "Bad gateway, server temporarily unavailable",
"type": "bad_gateway"
}
}
curl --request POST \
--url https://api.apimart.ai/v1/images/generations \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"model": "gpt-image-1-official",
"prompt": "An ancient castle under a starry sky",
"size": "1:1",
"quality": "auto",
"n": 1
}'
import requests
url = "https://api.apimart.ai/v1/images/generations"
payload = {
"model": "gpt-image-1-official",
"prompt": "An ancient castle under a starry sky",
"size": "1:1",
"quality": "auto",
"n": 1
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.json())
const url = "https://api.apimart.ai/v1/images/generations";
const payload = {
model: "gpt-image-1-official",
prompt: "An ancient castle under a starry sky",
size: "1:1",
quality: "auto",
n: 1,
};
const headers = {
Authorization: "Bearer <token>",
"Content-Type": "application/json",
};
fetch(url, {
method: "POST",
headers: headers,
body: JSON.stringify(payload),
})
.then((response) => response.json())
.then((data) => console.log(data))
.catch((error) => console.error("Error:", error));
package main
import (
"bytes"
"encoding/json"
"fmt"
"io/ioutil"
"net/http"
)
func main() {
url := "https://api.apimart.ai/v1/images/generations"
payload := map[string]interface{}{
"model": "gpt-image-1-official",
"prompt": "An ancient castle under a starry sky",
"size": "1:1",
"quality": "auto",
"n": 1,
}
jsonData, _ := json.Marshal(payload)
req, _ := http.NewRequest("POST", url, bytes.NewBuffer(jsonData))
req.Header.Set("Authorization", "Bearer <token>")
req.Header.Set("Content-Type", "application/json")
client := &http.Client{}
resp, err := client.Do(req)
if err != nil {
panic(err)
}
defer resp.Body.Close()
body, _ := ioutil.ReadAll(resp.Body)
fmt.Println(string(body))
}
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;
import java.net.URI;
public class Main {
public static void main(String[] args) throws Exception {
String url = "https://api.apimart.ai/v1/images/generations";
String payload = """
{
"model": "gpt-image-1-official",
"prompt": "An ancient castle under a starry sky",
"size": "1:1",
"quality": "auto",
"n": 1
}
""";
HttpClient client = HttpClient.newHttpClient();
HttpRequest request = HttpRequest.newBuilder()
.uri(URI.create(url))
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.POST(HttpRequest.BodyPublishers.ofString(payload))
.build();
HttpResponse<String> response = client.send(request,
HttpResponse.BodyHandlers.ofString());
System.out.println(response.body());
}
}
<?php
$url = "https://api.apimart.ai/v1/images/generations";
$payload = [
"model" => "gpt-image-1-official",
"prompt" => "An ancient castle under a starry sky",
"size" => "1:1",
"quality" => "auto",
"n" => 1
];
$ch = curl_init($url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($payload));
curl_setopt($ch, CURLOPT_HTTPHEADER, [
"Authorization: Bearer <token>",
"Content-Type: application/json"
]);
$response = curl_exec($ch);
curl_close($ch);
echo $response;
?>
require 'net/http'
require 'json'
require 'uri'
url = URI("https://api.apimart.ai/v1/images/generations")
payload = {
model: "gpt-image-1-official",
prompt: "An ancient castle under a starry sky",
size: "1:1",
quality: "auto",
n: 1
}
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = "Bearer <token>"
request["Content-Type"] = "application/json"
request.body = payload.to_json
response = http.request(request)
puts response.body
import Foundation
let url = URL(string: "https://api.apimart.ai/v1/images/generations")!
let payload: [String: Any] = [
"model": "gpt-image-1-official",
"prompt": "An ancient castle under a starry sky",
"size": "1:1",
"quality": "auto",
"n": 1
]
var request = URLRequest(url: url)
request.httpMethod = "POST"
request.setValue("Bearer <token>", forHTTPHeaderField: "Authorization")
request.setValue("application/json", forHTTPHeaderField: "Content-Type")
request.httpBody = try? JSONSerialization.data(withJSONObject: payload)
let task = URLSession.shared.dataTask(with: request) { data, response, error in
if let error = error {
print("Error: \(error)")
return
}
if let data = data, let responseString = String(data: data, encoding: .utf8) {
print(responseString)
}
}
task.resume()
using System;
using System.Net.Http;
using System.Text;
using System.Threading.Tasks;
class Program
{
static async Task Main(string[] args)
{
var url = "https://api.apimart.ai/v1/images/generations";
var payload = @"{
""model"": ""gpt-image-1-official"",
""prompt"": ""An ancient castle under a starry sky"",
""size"": ""1:1"",
""quality"": ""auto"",
""n"": 1
}";
using var client = new HttpClient();
client.DefaultRequestHeaders.Add("Authorization", "Bearer <token>");
var content = new StringContent(payload, Encoding.UTF8, "application/json");
var response = await client.PostAsync(url, content);
var result = await response.Content.ReadAsStringAsync();
Console.WriteLine(result);
}
}
import 'dart:convert';
import 'package:http/http.dart' as http;
void main() async {
final url = Uri.parse('https://api.apimart.ai/v1/images/generations');
final payload = {
'model': 'gpt-image-1-official',
'prompt': 'An ancient castle under a starry sky',
'size': '1:1',
'quality': 'auto',
'n': 1,
};
final response = await http.post(
url,
headers: {
'Authorization': 'Bearer <token>',
'Content-Type': 'application/json',
},
body: jsonEncode(payload),
);
print(response.body);
}
library(httr)
library(jsonlite)
url <- "https://api.apimart.ai/v1/images/generations"
payload <- list(
model = "gpt-image-1-official",
prompt = "An ancient castle under a starry sky",
size = "1:1",
quality = "auto",
n = 1
)
response <- POST(
url,
add_headers(
Authorization = "Bearer <token>",
`Content-Type` = "application/json"
),
body = toJSON(payload, auto_unbox = TRUE),
encode = "raw"
)
cat(content(response, "text"))
{
"code": 200,
"data": [
{
"status": "submitted",
"task_id": "task_01KXXXXXXXXXXXXXXX"
}
]
}
{
"error": {
"code": 400,
"message": "Invalid request parameters",
"type": "invalid_request_error"
}
}
{
"error": {
"code": 401,
"message": "Authentication failed, please check your API key",
"type": "authentication_error"
}
}
{
"error": {
"code": 402,
"message": "Insufficient balance, please top up and try again",
"type": "payment_required"
}
}
{
"error": {
"code": 403,
"message": "Access forbidden, you do not have permission to access this resource",
"type": "permission_error"
}
}
{
"error": {
"code": 429,
"message": "Too many requests, please try again later",
"type": "rate_limit_error"
}
}
{
"error": {
"code": 500,
"message": "Internal server error, please try again later",
"type": "server_error"
}
}
{
"error": {
"code": 502,
"message": "Bad gateway, server temporarily unavailable",
"type": "bad_gateway"
}
}
Modèles pris en charge
| Modèle | Description | Modes | Image-vers-image | Max d’images | Facturation |
|---|---|---|---|---|---|
gpt-image-1-official | Priorité à la stabilité, adapté à la génération d’images générale | Texte-vers-image / Image-vers-image | Pris en charge | 4 | Size × Quality |
gpt-image-1.5-official | Nouvelle version, adaptée à une qualité supérieure et à l’édition complexe | Texte-vers-image / Image-vers-image | Pris en charge | 4 | Size × Quality |
Autorisations
string
requis
Toutes les requêtes API nécessitent une authentification Bearer TokenObtenir votre clé API :Rendez-vous sur la page de gestion des clés API pour obtenir votre clé APIAjoutez ce qui suit aux en-têtes de votre requête :
Authorization: Bearer YOUR_API_KEY
Body
string
requis
Nom du modèle
gpt-image-1-official— Priorité à la stabilité, adapté à la génération d’images généralegpt-image-1.5-official— Nouvelle version, adaptée à une qualité supérieure et à l’édition complexe
boolean
défaut:"false"
Indique s’il faut modérer le contenu avant d’envoyer la tâche d’image.
true: vérifier les prompts et les images d’entrée avecomni-moderation-latestfalseou omis : ne pas envoyer de requête de modération, sans coût ni latence de modération supplémentaires (par défaut)
string
requis
Description textuelle pour la génération d’images, prend en charge à la fois le chinois et l’anglais
string
défaut:"1:1"
Ratio d’aspectRatios pris en charge :
1:1— Carré (par défaut)3:2— Paysage2:3— Portrait
integer
défaut:"1"
Nombre d’images à générerPlage : 1-4
- Les valeurs ≤ 0 seront traitées comme
1 - Les valeurs > 4 seront traitées comme
4
1), sans guillemets, sinon une erreur sera renvoyéestring
défaut:"auto"
Qualité de l’image
auto— Sélection automatique de la qualité (par défaut)low— Plus rapide, plus économiquemedium— Équilibre entre qualité et coûthigh— Qualité supérieure, coût plus élevé
string
défaut:"auto"
Mode d’arrière-plan
auto— Arrière-plan automatique (par défaut)opaque— Arrière-plan opaquetransparent— Arrière-plan transparent, recommandé avec le format de sortiepng
background: transparent ne peut pas être utilisé simultanément avec output_format: jpegstring
défaut:"auto"
Niveau de modération
auto— Niveau de modération par défautlow— Modération plus permissive
string
défaut:"png"
Format de sortie
png— Format par défaut, adapté aux arrière-plans transparentsjpeg— Taille de fichier plus petite, adapté à la sortie d’images générale
background: transparent ne peut pas être utilisé simultanément avec output_format: jpeginteger
Niveau de compression de sortie, plage 0-100
- Recommandé uniquement pour
jpeg - Non recommandé pour
png
array
Tableau d’URL d’images de référence, active le mode image-vers-image lorsqu’il est fourni
Limite : Jusqu’à 15 images de référence
Afficher Détails
Afficher Détails
- 1 image pour l’édition avec une référence unique
- 2 à 15 images pour la fusion d’éditions avec plusieurs références
- Plus de 15 images seront rejetées
- Doivent être des URL d’images publiquement accessibles et stables
string
URL de l’image de masque pour l’inpainting
- Doit être utilisé conjointement avec
image_urls - Sera soumis via l’API d’édition officielle
- Avant de téléverser l’image de masque, veuillez confirmer que le canal Alpha de l’image est « Oui ».
- La taille de l’image de masque doit correspondre à la première image de référence.
Référence des tailles
Les ratios d’aspect sont utilisés en externe ; le système les associe automatiquement aux dimensions officielles en interne.| Ratio | Taille effective | Description |
|---|---|---|
1:1 | 1024x1024 | Carré |
2:3 | 1024x1536 | Portrait |
3:2 | 1536x1024 | Paysage |
Exemples d’utilisation
Texte-vers-image (minimal){
"model": "gpt-image-1-official",
"prompt": "An ancient castle under a starry sky"
}
{
"model": "gpt-image-1-official",
"prompt": "A flat icon of a glass bottle with no background",
"size": "2:3",
"quality": "high",
"background": "transparent",
"moderation": "low",
"output_format": "png",
"n": 1
}
{
"model": "gpt-image-1.5-official",
"prompt": "Convert the reference image to illustration style, preserving the main outline",
"size": "1:1",
"quality": "auto",
"image_urls": [
"https://your-cdn.com/input.png"
],
"n": 1
}
{
"model": "gpt-image-1.5-official",
"prompt": "Merge two reference images into an illustration poster, preserving the main outlines",
"size": "1:1",
"quality": "auto",
"background": "transparent",
"image_urls": [
"https://your-cdn.com/input-a.png",
"https://your-cdn.com/input-b.png"
],
"moderation": "low",
"output_format": "png",
"n": 1
}
{
"model": "gpt-image-1-official",
"prompt": "Four minimalist poster variations of a red fox",
"size": "1:1",
"quality": "low",
"output_format": "png",
"n": 4
}
Response
integer
Code de statut de la réponse
array
Notes
- Traitement asynchrone : Après soumission, un
task_idest renvoyé. Interrogez/v1/tasks/{task_id}pour obtenir les résultats - Sélection du modèle : Utilisez
gpt-image-1-officialpour la génération d’images générale ; utilisezgpt-image-1.5-officialpour l’édition de haute qualité et les tâches image-vers-image complexes - Exigences relatives aux URL d’images : Pour image-vers-image, utilisez des URL d’images publiquement accessibles et stables
- Facturation : Facturé pour chaque image générée avec succès ; aucun frais en cas d’échec
⌘I