Interface mj-v8.2-edit
curl --request POST \
--url https://api.evolink.ai/v1/images/generations \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "mj-v8.2-edit",
"prompt": "Beautiful mountain scenery background",
"model_params": {
"task_id": "task-unified-xxx",
"image_number": 0,
"canvas": {
"width": 1024,
"height": 1024
},
"img_pos": {
"width": 912,
"height": 512,
"x": 56,
"y": 256
},
"speed": "fast"
}
}
'import requests
url = "https://api.evolink.ai/v1/images/generations"
payload = {
"model": "mj-v8.2-edit",
"prompt": "Beautiful mountain scenery background",
"model_params": {
"task_id": "task-unified-xxx",
"image_number": 0,
"canvas": {
"width": 1024,
"height": 1024
},
"img_pos": {
"width": 912,
"height": 512,
"x": 56,
"y": 256
},
"speed": "fast"
}
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
model: 'mj-v8.2-edit',
prompt: 'Beautiful mountain scenery background',
model_params: {
task_id: 'task-unified-xxx',
image_number: 0,
canvas: {width: 1024, height: 1024},
img_pos: {width: 912, height: 512, x: 56, y: 256},
speed: 'fast'
}
})
};
fetch('https://api.evolink.ai/v1/images/generations', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.evolink.ai/v1/images/generations",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'model' => 'mj-v8.2-edit',
'prompt' => 'Beautiful mountain scenery background',
'model_params' => [
'task_id' => 'task-unified-xxx',
'image_number' => 0,
'canvas' => [
'width' => 1024,
'height' => 1024
],
'img_pos' => [
'width' => 912,
'height' => 512,
'x' => 56,
'y' => 256
],
'speed' => 'fast'
]
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.evolink.ai/v1/images/generations"
payload := strings.NewReader("{\n \"model\": \"mj-v8.2-edit\",\n \"prompt\": \"Beautiful mountain scenery background\",\n \"model_params\": {\n \"task_id\": \"task-unified-xxx\",\n \"image_number\": 0,\n \"canvas\": {\n \"width\": 1024,\n \"height\": 1024\n },\n \"img_pos\": {\n \"width\": 912,\n \"height\": 512,\n \"x\": 56,\n \"y\": 256\n },\n \"speed\": \"fast\"\n }\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://api.evolink.ai/v1/images/generations")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"model\": \"mj-v8.2-edit\",\n \"prompt\": \"Beautiful mountain scenery background\",\n \"model_params\": {\n \"task_id\": \"task-unified-xxx\",\n \"image_number\": 0,\n \"canvas\": {\n \"width\": 1024,\n \"height\": 1024\n },\n \"img_pos\": {\n \"width\": 912,\n \"height\": 512,\n \"x\": 56,\n \"y\": 256\n },\n \"speed\": \"fast\"\n }\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.evolink.ai/v1/images/generations")
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 = "{\n \"model\": \"mj-v8.2-edit\",\n \"prompt\": \"Beautiful mountain scenery background\",\n \"model_params\": {\n \"task_id\": \"task-unified-xxx\",\n \"image_number\": 0,\n \"canvas\": {\n \"width\": 1024,\n \"height\": 1024\n },\n \"img_pos\": {\n \"width\": 912,\n \"height\": 512,\n \"x\": 56,\n \"y\": 256\n },\n \"speed\": \"fast\"\n }\n}"
response = http.request(request)
puts response.read_body{
"created": 1757165031,
"id": "task-unified-1757165031-mjv82",
"model": "<string>",
"object": "image.generation.task",
"progress": 0,
"status": "processing",
"task_info": {
"estimated_time": 60
},
"type": "image",
"usage": {
"billing_rule": "per_call",
"credits_reserved": 8.1,
"user_group": "default"
}
}{
"error": {
"code": "invalid_request",
"message": "Invalid request parameters",
"type": "invalid_request_error"
}
}{
"error": {
"code": "unauthorized",
"message": "Invalid or expired token",
"type": "authentication_error"
}
}{
"error": {
"code": "insufficient_quota",
"message": "Insufficient quota. Please top up your account.",
"type": "insufficient_quota"
}
}{
"error": {
"code": "model_access_denied",
"message": "Token does not have access to model: mj-v8.2-edit",
"type": "invalid_request_error"
}
}{
"error": {
"code": "rate_limit_exceeded",
"message": "Too many requests, please try again later",
"type": "rate_limit_error"
}
}{
"error": {
"code": "internal_error",
"message": "Internal server error",
"type": "api_error"
}
}Midjourney V8.2
Midjourney V8.2 Édition de canevas
- Repositionne l’image d’une tâche existante sur le canevas et remplit les zones vides avec l’IA
- Adapté à l’ajustement de la composition, l’extension de scènes (outpaint), la repeinture, etc.
- Remarque : les tâches dérivées d’images V8.2 (variation / remix / édition) sont rendues côté fournisseur par le moteur V7 (documenté par le canal fournisseur) ; le résultat peut différer légèrement en style de l’image source. La facturation reste inchangée
- Mode de traitement asynchrone, utilisez l’ID de tâche retourné pour effectuer une requête
POST
/
v1
/
images
/
generations
Interface mj-v8.2-edit
curl --request POST \
--url https://api.evolink.ai/v1/images/generations \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "mj-v8.2-edit",
"prompt": "Beautiful mountain scenery background",
"model_params": {
"task_id": "task-unified-xxx",
"image_number": 0,
"canvas": {
"width": 1024,
"height": 1024
},
"img_pos": {
"width": 912,
"height": 512,
"x": 56,
"y": 256
},
"speed": "fast"
}
}
'import requests
url = "https://api.evolink.ai/v1/images/generations"
payload = {
"model": "mj-v8.2-edit",
"prompt": "Beautiful mountain scenery background",
"model_params": {
"task_id": "task-unified-xxx",
"image_number": 0,
"canvas": {
"width": 1024,
"height": 1024
},
"img_pos": {
"width": 912,
"height": 512,
"x": 56,
"y": 256
},
"speed": "fast"
}
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
model: 'mj-v8.2-edit',
prompt: 'Beautiful mountain scenery background',
model_params: {
task_id: 'task-unified-xxx',
image_number: 0,
canvas: {width: 1024, height: 1024},
img_pos: {width: 912, height: 512, x: 56, y: 256},
speed: 'fast'
}
})
};
fetch('https://api.evolink.ai/v1/images/generations', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.evolink.ai/v1/images/generations",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'model' => 'mj-v8.2-edit',
'prompt' => 'Beautiful mountain scenery background',
'model_params' => [
'task_id' => 'task-unified-xxx',
'image_number' => 0,
'canvas' => [
'width' => 1024,
'height' => 1024
],
'img_pos' => [
'width' => 912,
'height' => 512,
'x' => 56,
'y' => 256
],
'speed' => 'fast'
]
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.evolink.ai/v1/images/generations"
payload := strings.NewReader("{\n \"model\": \"mj-v8.2-edit\",\n \"prompt\": \"Beautiful mountain scenery background\",\n \"model_params\": {\n \"task_id\": \"task-unified-xxx\",\n \"image_number\": 0,\n \"canvas\": {\n \"width\": 1024,\n \"height\": 1024\n },\n \"img_pos\": {\n \"width\": 912,\n \"height\": 512,\n \"x\": 56,\n \"y\": 256\n },\n \"speed\": \"fast\"\n }\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://api.evolink.ai/v1/images/generations")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"model\": \"mj-v8.2-edit\",\n \"prompt\": \"Beautiful mountain scenery background\",\n \"model_params\": {\n \"task_id\": \"task-unified-xxx\",\n \"image_number\": 0,\n \"canvas\": {\n \"width\": 1024,\n \"height\": 1024\n },\n \"img_pos\": {\n \"width\": 912,\n \"height\": 512,\n \"x\": 56,\n \"y\": 256\n },\n \"speed\": \"fast\"\n }\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.evolink.ai/v1/images/generations")
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 = "{\n \"model\": \"mj-v8.2-edit\",\n \"prompt\": \"Beautiful mountain scenery background\",\n \"model_params\": {\n \"task_id\": \"task-unified-xxx\",\n \"image_number\": 0,\n \"canvas\": {\n \"width\": 1024,\n \"height\": 1024\n },\n \"img_pos\": {\n \"width\": 912,\n \"height\": 512,\n \"x\": 56,\n \"y\": 256\n },\n \"speed\": \"fast\"\n }\n}"
response = http.request(request)
puts response.read_body{
"created": 1757165031,
"id": "task-unified-1757165031-mjv82",
"model": "<string>",
"object": "image.generation.task",
"progress": 0,
"status": "processing",
"task_info": {
"estimated_time": 60
},
"type": "image",
"usage": {
"billing_rule": "per_call",
"credits_reserved": 8.1,
"user_group": "default"
}
}{
"error": {
"code": "invalid_request",
"message": "Invalid request parameters",
"type": "invalid_request_error"
}
}{
"error": {
"code": "unauthorized",
"message": "Invalid or expired token",
"type": "authentication_error"
}
}{
"error": {
"code": "insufficient_quota",
"message": "Insufficient quota. Please top up your account.",
"type": "insufficient_quota"
}
}{
"error": {
"code": "model_access_denied",
"message": "Token does not have access to model: mj-v8.2-edit",
"type": "invalid_request_error"
}
}{
"error": {
"code": "rate_limit_exceeded",
"message": "Too many requests, please try again later",
"type": "rate_limit_error"
}
}{
"error": {
"code": "internal_error",
"message": "Internal server error",
"type": "api_error"
}
}Midjourney dispose d’un système de modération de contenu intégré. Chaque image est modérée individuellement : les images filtrées n’apparaissent pas dans les résultats et les autres images sont livrées normalement, vous pouvez donc recevoir moins d’images que d’habitude. Si au moins une image est validée, la tâche est
completed et facturée normalement ; si toutes les images sont filtrées, la tâche se termine en failed et les crédits réservés sont intégralement remboursés. Veuillez vous assurer que vos prompts et vos images de référence respectent les directives de contenu.Autorisations
Toutes les interfaces nécessitent une authentification par Bearer Token
Obtenir une clé API :
Visitez la page de gestion des clés API pour obtenir votre clé API
Ajoutez dans l'en-tête de la requête :
Authorization: Bearer YOUR_API_KEY
Corps
application/json
Adresse de rappel HTTPS après l'achèvement de la tâche
Moment du rappel :
- Déclenché lorsque la tâche est terminée ou échouée
- Envoyé après la confirmation de facturation
Restrictions de sécurité :
- Seul le protocole HTTPS est pris en charge
- Les rappels vers les adresses IP privées sont interdits (127.0.0.1, 10.x.x.x, 172.16-31.x.x, 192.168.x.x, etc.)
- La longueur de l'URL ne doit pas dépasser
2048caractères
Mécanisme de rappel :
- Délai d'expiration :
10secondes - Jusqu'à
3tentatives après un échec (respectivement1s/2s/4s après l'échec) - Le format du corps de la réponse de rappel est identique à celui de l'interface de requête de tâche
- Un code de statut 2xx est considéré comme un succès, tout autre code de statut déclenche une nouvelle tentative
Exemple:
"https://your-domain.com/webhooks/image-task-completed"
Réponse
Tâche de génération d'images créée avec succès