
Qwen-Image Text-to-Image Max API by Alibaba
General-purpose image generation model that supports various art styles and is particularly good at rendering complex text.
コード例
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/text-to-image-max",
"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()インストール
お使いの言語に必要なパッケージをインストールしてください。
pip install requests認証
すべての API リクエストには API キーによる認証が必要です。API キーは Atlas Cloud ダッシュボードから取得できます。
export ATLASCLOUD_API_KEY="your-api-key-here"HTTP ヘッダー
import os
API_KEY = os.environ.get("ATLASCLOUD_API_KEY")
headers = {
"Content-Type": "application/json",
"Authorization": f"Bearer {API_KEY}"
}API キーをクライアントサイドのコードや公開リポジトリに公開しないでください。代わりに環境変数またはバックエンドプロキシを使用してください。
リクエストを送信
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())リクエストを送信
非同期生成リクエストを送信します。API は予測 ID を返し、それを使用してステータスの確認や結果の取得ができます。
/api/v1/model/generateImageリクエストボディ
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/text-to-image-max",
"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']}")レスポンス
{
"id": "pred_abc123",
"status": "processing",
"model": "model-name",
"created_at": "2025-01-01T00:00:00Z"
}ステータスを確認
予測エンドポイントをポーリングして、リクエストの現在のステータスを確認します。
/api/v1/model/prediction/{prediction_id}ポーリング例
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)ステータス値
processingリクエストはまだ処理中です。completed生成が完了しました。出力が利用可能です。succeeded生成が成功しました。出力が利用可能です。failed生成に失敗しました。エラーフィールドを確認してください。完了レスポンス
{
"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"
}
}ファイルをアップロード
Atlas Cloud ストレージにファイルをアップロードし、API リクエストで使用できる URL を取得します。multipart/form-data を使用してアップロードします。
/api/v1/model/uploadMediaアップロード例
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}")レスポンス
{
"data": {
"download_url": "https://storage.atlascloud.ai/uploads/abc123/image.png",
"file_name": "image.png",
"content_type": "image/png",
"size": 1024000
}
}入力 Schema
以下のパラメータがリクエストボディで使用できます。
利用可能なパラメータはありません。
リクエストボディの例
{
"model": "alibaba/qwen-image/text-to-image-max"
}出力 Schema
API は生成された出力 URL を含む予測レスポンスを返します。
レスポンス例
{
"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 は 300 以上の AI モデルを AI コーディングアシスタントに直接統合します。ワンコマンドでインストールし、自然言語で画像・動画生成や LLM との対話が可能です。
対応クライアント
インストール
npx skills add AtlasCloudAI/atlas-cloud-skillsAPI キーの設定
Atlas Cloud ダッシュボードから API キーを取得し、環境変数として設定してください。
export ATLASCLOUD_API_KEY="your-api-key-here"機能
インストール後、AI アシスタントで自然言語を使用してすべての Atlas Cloud モデルにアクセスできます。
MCP Server
Atlas Cloud MCP Server は Model Context Protocol を通じて IDE と 300 以上の AI モデルを接続します。MCP 対応のあらゆるクライアントで動作します。
対応クライアント
インストール
npx -y atlascloud-mcp設定
以下の設定を IDE の MCP 設定ファイルに追加してください。
{
"mcpServers": {
"atlascloud": {
"command": "npx",
"args": [
"-y",
"atlascloud-mcp"
],
"env": {
"ATLASCLOUD_API_KEY": "your-api-key-here"
}
}
}
}利用可能なツール
APIスキーマ
スキーマが利用できません利用可能な例がありません
Alibaba Qwen-Image Text-to-Image Max
The flagship text-to-image generation model from Alibaba Cloud, designed to deliver state-of-the-art visual quality, exceptional prompt adherence, and rich artistic detail. Qwen-Image Max represents the pinnacle of the Qwen-Image family, capable of transforming complex text descriptions into stunning, high-resolution visuals suitable for professional and creative workflows.
Overview
- Purpose: Generate premium-quality images from natural language descriptions.
- Core Capability: Industry-leading visual fidelity with deep semantic understanding of prompts.
- Foundation: Built on Alibaba's advanced large-scale multi-modal architecture.
- Typical Output: High-resolution, photorealistic or artistic images with precise lighting, texture, and composition.
- Use Cases: Professional design, advertising creatives, concept art, marketing materials, and high-end content creation.
Key Features
- Superior Visual Quality: Delivers the highest level of detail, texture, and lighting realism available in the Qwen-Image series.
- Complex Prompt Understanding: Accurately interprets long, intricate prompts, including spatial relationships, artistic styles, and specific object attributes.
- Text Rendering: Enhanced capability to render legible text within generated images (e.g., signboards, posters).
- Style Versatility: Masterfully handles a wide range of styles, from photorealism and cinematic shots to 3D render, oil painting, and illustration.
- High Resolution: Supports generation of high-definition images suitable for professional use.
Designed For
- Professional Designers: Create high-quality assets, mockups, and final visuals.
- Digital Artists: Explore complex concepts and generate detailed artwork.
- Marketing Agencies: Produce campaign-ready visuals with specific brand requirements.
- Enterprise Users: High-demand use cases requiring consistent, top-tier visual output.
Input Requirements
To achieve the best results, follow these guidelines:
Text Prompt
- Content: Detailed English descriptions of the subject, setting, lighting, style, and mood.
- Length: Supports long context, but concise and descriptive prompts often yield the best focus.
- Negative Prompt: Optional. Specify elements to exclude (e.g., "blur, low quality, distortion").
Parameters
- Aspect Ratio: Supports various standard ratios (1:1, 16:9, 9:16, 4:3, 3:4).
- Resolution: Optimized for high-resolution outputs (e.g., 1024x1024 and above).
- Steps/Guidance: Configurable for fine-tuning the balance between prompt adherence and image quality.
Pricing
Billing is typically based on the number of images generated and the resolution selected.
- Billing Logic: Per-image generation cost.
- Tier: "Max" tier commands a premium rate due to higher computational resources and output quality compared to standard models.
How to Use
- Enter Prompt: Describe the image you want to generate in detail.
- Set Parameters: Choose your desired aspect ratio and number of images.
- Generate: Submit the request to the Qwen-Image Max model.
- Refine: Use the generated image as a reference or adjust the prompt for iterations.
Best Practices
- Be Specific: Instead of "a cat," try "a fluffy white Persian cat sitting on a velvet sofa, cinematic lighting, 8k resolution."
- Define Style: Explicitly state the medium (e.g., "oil painting," "photograph," "3D render").
- Lighting & Composition: Mention lighting conditions (e.g., "golden hour," "studio lighting") and camera angles.
- Iterate: If the first result isn't perfect, tweak the prompt or use a negative prompt to remove unwanted elements.
Limitations
- Text Accuracy: While improved, complex or long text strings within the image may still occasionally have minor errors.
- Spatial Logic: Extremely complex spatial arrangements might sometimes require prompt tuning.
Version
- Model: Alibaba Qwen-Image Text-to-Image Max
- Family: Qwen-Image
- Technical Context: Large-scale diffusion transformer model optimized for maximum visual fidelity.






