aliyun-image

Alibaba Cloud Bailian Image Generation and Editing

🔄 Synchronized updates: This project is released simultaneously on GitHub and ClawHub .

Quick Start

Prerequisites

# 配置 API Key
export DASHSCOPE_API_KEY="sk-xxxx"

Text-to-Image

import os, requests

resp = requests.post( "https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation", headers={"Authorization": f"Bearer {os.getenv('DASHSCOPE_API_KEY')}"}, json={ "model": "qwen-image-plus", "input": {"messages": [{"role": "user", "content": [{"text": "An orange cat dozing in the sunlight"}]}]}, "parameters": {"prompt_extend": True, "watermark": False} } ) print(resp.json()["output"]["choices"][0]["message"]["content"][0]["image"])

### 图像编辑

```python
resp = requests.post(
    "https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation",
    headers={"Authorization": f"Bearer {os.getenv('DASHSCOPE_API_KEY')}"},
    json={
        "model": "qwen-image-edit-plus",
        "input": {"messages": [{"role": "user", "content": [
            {"image": "https://example.com/photo.jpg"},
            {"text": "把背景换成星空"}
        ]}]},
        "parameters": {"prompt_extend": True, "watermark": False}
    }
)
print(resp.json()["output"]["choices"][0]["message"]["content"][0]["image"])

Image Translation

import os, requests, time

# 1. 创建翻译任务
resp = requests.post(
    "https://dashscope.aliyuncs.com/api/v1/services/aigc/image2image/image-synthesis",
    headers={
        "Authorization": f"Bearer {os.getenv('DASHSCOPE_API_KEY')}",
        "X-DashScope-Async": "enable"
    },
    json={
        "model": "qwen-mt-image",
        "input": {
            "image_url": "https://example.com/english-poster.jpg",
            "source_lang": "en",
            "target_lang": "zh"
        }
    }
)
task_id = resp.json()["output"]["task_id"]

# 2. 轮询获取结果
while True:
    time.sleep(3)
    result = requests.get(
        f"https://dashscope.aliyuncs.com/api/v1/tasks/{task_id}",
        headers={"Authorization": f"Bearer {os.getenv('DASHSCOPE_API_KEY')}"}
    ).json()
    if result["output"]["task_status"] == "SUCCEEDED":
        print(result["output"]["image_url"])
        break

---

Default Configuration

Scenario	Default Model	High-Quality Model
Text-to-Image	qwen-image-plus	qwen-image-max
Image Editing	qwen-image-edit-plus	qwen-image-edit-max
Image Translation	qwen-mt-image	-

Rule: Use the Plus series by default; use the Max series only when the user explicitly requests "the best" or "the highest quality".

Default Parameters

{
  "negative_prompt": "低分辨率，低画质，肢体畸形，手指畸形，画面过饱和，蜡像感",
  "prompt_extend": true,
  "watermark": false
}

---

Detailed Reference

Load the following documents on demand:

Document	Purpose
references/text-to-image.md	Complete API reference for text-to-image: model list, resolution, all parameters
references/image-edit.md	Complete API reference for image editing: single-image editing, multi-image fusion, input requirements
references/image-translate.md	Complete API reference for image translation: supported languages, asynchronous calls, terminology definitions

---

Tool Scripts

Script	Purpose
scripts/client.py	A pre-packaged API client that supports text-to-image, image editing, and image translation

Using the Script：

# 文生图
python scripts/client.py generate "一只橘猫在阳光下打盹" --size 1920*1080

# 图像编辑
python scripts/client.py edit "https://example.com/photo.jpg" "把背景换成星空" -n 2

# 图像翻译
python scripts/client.py translate "https://example.com/english.jpg" --source en --target zh

---

Key Notes

1. Image URL Validity Period: Generated image URLs are retained only for 24 hours, please download them promptly
2. Region: The API Key and request URL must belong to the same region (Beijing/Singapore)
3. Fees: Billing is based on the number of successfully generated images

---

Common Errors

Error Code	Cause	Solution
InvalidApiKey	Invalid API Key	Check the environment variable configuration
InvalidParameter	Parameter error	Check the request format
DataInspectionFailed	Content review failed	Modify the input content