
Qwen-Image Edit Plus API by Alibaba
Supports multiple image inputs and outputs, allowing for precise modification of text within images, addition, deletion, or movement of objects, alteration of subject actions, transfer of image styles, and enhancement of image details.
Eingabe
Ausgabe
InaktivJede Ausführung kostet $0.021. Für $10 können Sie ca. 476 Mal ausführen.
Sie können fortfahren mit:
Codebeispiel
import requests
import time
# Step 1: Start image generation
generate_url = "https://api.atlascloud.ai/api/v1/model/generateImage"
headers = {
"Content-Type": "application/json",
"Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
"model": "alibaba/qwen-image/edit-plus",
"prompt": "A beautiful landscape with mountains and lake",
"width": 512,
"height": 512,
"steps": 20,
"guidance_scale": 7.5,
}
generate_response = requests.post(generate_url, headers=headers, json=data)
generate_result = generate_response.json()
prediction_id = generate_result["data"]["id"]
# Step 2: Poll for result
poll_url = f"https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}"
def check_status():
while True:
response = requests.get(poll_url, headers={"Authorization": "Bearer $ATLASCLOUD_API_KEY"})
result = response.json()
if result["data"]["status"] == "completed":
print("Generated image:", result["data"]["outputs"][0])
return result["data"]["outputs"][0]
elif result["data"]["status"] == "failed":
raise Exception(result["data"]["error"] or "Generation failed")
else:
# Still processing, wait 2 seconds
time.sleep(2)
image_url = check_status()Installieren
Installieren Sie das erforderliche Paket für Ihre Programmiersprache.
pip install requestsAuthentifizierung
Alle API-Anfragen erfordern eine Authentifizierung über einen API-Schlüssel. Sie können Ihren API-Schlüssel über das Atlas Cloud Dashboard erhalten.
export ATLASCLOUD_API_KEY="your-api-key-here"HTTP-Header
import os
API_KEY = os.environ.get("ATLASCLOUD_API_KEY")
headers = {
"Content-Type": "application/json",
"Authorization": f"Bearer {API_KEY}"
}Geben Sie Ihren API-Schlüssel niemals in clientseitigem Code oder öffentlichen Repositories preis. Verwenden Sie stattdessen Umgebungsvariablen oder einen Backend-Proxy.
Anfrage senden
import requests
url = "https://api.atlascloud.ai/api/v1/model/generateImage"
headers = {
"Content-Type": "application/json",
"Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
"model": "your-model",
"prompt": "A beautiful landscape"
}
response = requests.post(url, headers=headers, json=data)
print(response.json())Anfrage senden
Senden Sie eine asynchrone Generierungsanfrage. Die API gibt eine Vorhersage-ID zurück, mit der Sie den Status prüfen und das Ergebnis abrufen können.
/api/v1/model/generateImageAnfragekörper
import requests
url = "https://api.atlascloud.ai/api/v1/model/generateImage"
headers = {
"Content-Type": "application/json",
"Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
"model": "alibaba/qwen-image/edit-plus",
"input": {
"prompt": "A beautiful landscape with mountains and lake"
}
}
response = requests.post(url, headers=headers, json=data)
result = response.json()
print(f"Prediction ID: {result['id']}")
print(f"Status: {result['status']}")Antwort
{
"id": "pred_abc123",
"status": "processing",
"model": "model-name",
"created_at": "2025-01-01T00:00:00Z"
}Status prüfen
Fragen Sie den Vorhersage-Endpunkt ab, um den aktuellen Status Ihrer Anfrage zu überprüfen.
/api/v1/model/prediction/{prediction_id}Abfrage-Beispiel
import requests
import time
prediction_id = "pred_abc123"
url = f"https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}"
headers = { "Authorization": "Bearer $ATLASCLOUD_API_KEY" }
while True:
response = requests.get(url, headers=headers)
result = response.json()
status = result["data"]["status"]
print(f"Status: {status}")
if status in ["completed", "succeeded"]:
output_url = result["data"]["outputs"][0]
print(f"Output URL: {output_url}")
break
elif status == "failed":
print(f"Error: {result['data'].get('error', 'Unknown')}")
break
time.sleep(3)Statuswerte
processingDie Anfrage wird noch verarbeitet.completedDie Generierung ist abgeschlossen. Ergebnisse sind verfügbar.succeededDie Generierung war erfolgreich. Ergebnisse sind verfügbar.failedDie Generierung ist fehlgeschlagen. Überprüfen Sie das Fehlerfeld.Abgeschlossene Antwort
{
"data": {
"id": "pred_abc123",
"status": "completed",
"outputs": [
"https://storage.atlascloud.ai/outputs/result.png"
],
"metrics": {
"predict_time": 8.3
},
"created_at": "2025-01-01T00:00:00Z",
"completed_at": "2025-01-01T00:00:10Z"
}
}Dateien hochladen
Laden Sie Dateien in den Atlas Cloud Speicher hoch und erhalten Sie eine URL, die Sie in Ihren API-Anfragen verwenden können. Verwenden Sie multipart/form-data zum Hochladen.
/api/v1/model/uploadMediaUpload-Beispiel
import requests
url = "https://api.atlascloud.ai/api/v1/model/uploadMedia"
headers = { "Authorization": "Bearer $ATLASCLOUD_API_KEY" }
with open("image.png", "rb") as f:
files = {"file": ("image.png", f, "image/png")}
response = requests.post(url, headers=headers, files=files)
result = response.json()
download_url = result["data"]["download_url"]
print(f"File URL: {download_url}")Antwort
{
"data": {
"download_url": "https://storage.atlascloud.ai/uploads/abc123/image.png",
"file_name": "image.png",
"content_type": "image/png",
"size": 1024000
}
}Eingabe-Schema
Die folgenden Parameter werden im Anfragekörper akzeptiert.
Keine Parameter verfügbar.
Beispiel-Anfragekörper
{
"model": "alibaba/qwen-image/edit-plus"
}Ausgabe-Schema
Die API gibt eine Vorhersage-Antwort mit den generierten Ausgabe-URLs zurück.
Beispielantwort
{
"id": "pred_abc123",
"status": "completed",
"model": "model-name",
"outputs": [
"https://storage.atlascloud.ai/outputs/result.png"
],
"metrics": {
"predict_time": 8.3
},
"created_at": "2025-01-01T00:00:00Z",
"completed_at": "2025-01-01T00:00:10Z"
}Atlas Cloud Skills
Atlas Cloud Skills integriert über 300 KI-Modelle direkt in Ihren KI-Coding-Assistenten. Ein Befehl zur Installation, dann verwenden Sie natürliche Sprache, um Bilder, Videos zu generieren und mit LLMs zu chatten.
Unterstützte Clients
Installieren
npx skills add AtlasCloudAI/atlas-cloud-skillsAPI-Schlüssel einrichten
Erhalten Sie Ihren API-Schlüssel über das Atlas Cloud Dashboard und setzen Sie ihn als Umgebungsvariable.
export ATLASCLOUD_API_KEY="your-api-key-here"Funktionen
Nach der Installation können Sie natürliche Sprache in Ihrem KI-Assistenten verwenden, um auf alle Atlas Cloud Modelle zuzugreifen.
MCP-Server
Der Atlas Cloud MCP-Server verbindet Ihre IDE mit über 300 KI-Modellen über das Model Context Protocol. Funktioniert mit jedem MCP-kompatiblen Client.
Unterstützte Clients
Installieren
npx -y atlascloud-mcpKonfiguration
Fügen Sie die folgende Konfiguration zur MCP-Einstellungsdatei Ihrer IDE hinzu.
{
"mcpServers": {
"atlascloud": {
"command": "npx",
"args": [
"-y",
"atlascloud-mcp"
],
"env": {
"ATLASCLOUD_API_KEY": "your-api-key-here"
}
}
}
}Verfügbare Werkzeuge
API-Schema
Schema nicht verfügbarKeine Beispiele verfügbar
Anmelden, um Anfrageverlauf anzuzeigen
Sie müssen angemeldet sein, um auf Ihren Modellanfrageverlauf zuzugreifen.
AnmeldenAlibaba Qwen-Image Edit Plus
An advanced image editing model from Alibaba Cloud, offering precise control and high-quality results. Qwen-Image Edit Plus supports multi-image input and output, enabling complex tasks such as precise text modification, object addition/deletion/movement, action change, style transfer, and detail enhancement.
Overview
- Purpose: Perform precise image edits using text instructions.
- Core Capability: Supports single-image editing and multi-image blending.
- Foundation: Powered by Alibaba's advanced multi-modal generative AI technology.
- Typical Output: High-quality edited images (1-6 per request) that seamlessly blend changes with the original content.
- Use Cases: E-commerce product photography, professional photo retouching, creative design adjustments, and marketing asset generation.
Key Features
- Multi-image Blending:
- Example: Combine a girl from Image 1, wearing a skirt from Image 2, sitting in a pose from Image 3.
- Example: Combine a girl from Image 1, a necklace from Image 2, and a bag from Image 3.
- Single-image Editing:
- Generate depth-compliant images.
- Replace text (e.g., "HEALTH INSURANCE" -> "明天会更好").
- Replace shirt color.
- Change background (e.g., to Antarctica).
- High Fidelity: Preserves the quality, lighting, and texture of the original image while applying edits.
- Precise Editing: Capable of modifying text within images, adding/deleting/moving objects, changing subject actions, transferring styles, and enhancing details.
- Custom Resolution: Supports specifying output image resolution (512-2048px).
- Prompt Optimization: Supports intelligent prompt rewriting (
prompt_extend) for better results.
Designed For
- Designers: Quickly iterate on visual concepts and make adjustments.
- Photographers: Streamline retouching workflows.
- E-commerce Merchants: Modify product images for different contexts or variations.
- Developers: Build powerful image editing applications.
Input Requirements
To achieve the best results, follow these guidelines:
Inputs
- Structure:
messagesarray withrole: user.contentarray: 1-3 images ({"image": "..."}) + 1 text instruction ({"text": "..."}).
- Image Format: JPG, JPEG, PNG, BMP, TIFF, WEBP, GIF (first frame).
- Resolution: Recommended 384px - 3072px.
- Size Limit: Max 10MB per image.
- Text Limit: Max 800 characters.
Pricing
- Billing Logic: Pay-as-you-go based on the number of successful output images.
- Tier: "Plus" tier offers enhanced capabilities and higher precision compared to the standard version.
How to Use
- Prepare Inputs: Collect 1-3 reference images and define your text instruction.
- Configure Parameters: Set output count (
n), resolution (size), and other options. - Call API: Submit the request with the
messagesstructure containing images and text. - Review: Receive 1-6 edited images based on your specifications.
Limitations & FAQ
- Conversation: Does not support multi-turn conversation (single turn only).
- Languages: Chinese and English are supported; other languages are unverified.
- Aspect Ratio: Output follows the aspect ratio of the input image (or the last image if multiple are provided).
Version
- Model: Alibaba Qwen-Image Edit Plus
- Family: Qwen-Image
- Technical Context: Enhanced version with better detail, instruction following, and multi-image support.






