68 lines
1.4 KiB
Markdown
68 lines
1.4 KiB
Markdown
|
# Qwen-Image 文生图示例
|
|||
|
|
|
|||
|
|
使用阿里云 DashScope API 调用 **通义千问 Qwen-Image** 模型进行文生图。
|
|||
|
|
|
|||
|
|
## 快速开始
|
|||
|
|
|
|||
|
|
### 1. 配置 API Key
|
|||
|
|
|
|||
|
|
在 `.env` 文件中设置你的 DashScope API Key：
|
|||
|
|
|
|||
|
|
```env
|
|||
|
|
DASHSCOPE_API_KEY=sk-xxxxxxxx
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
> 获取 API Key: https://help.aliyun.com/zh/model-studio/get-api-key
|
|||
|
|
|
|||
|
|
### 2. 安装依赖
|
|||
|
|
|
|||
|
|
```bash
|
|||
|
|
uv sync
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
### 3. 运行示例
|
|||
|
|
|
|||
|
|
```bash
|
|||
|
|
uv run qwen_image_example.py
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
## 支持的模型
|
|||
|
|
|
|||
|
|
| 模型名称 | 说明 | 异步支持 |
|
|||
|
|
|---------|------|---------|
|
|||
|
|
| `qwen-image-plus` | 通用文生图模型 | ✅ |
|
|||
|
|
| `qwen-image-max` | 高质量文生图模型 | ❌ |
|
|||
|
|
|
|||
|
|
## 支持的分辨率
|
|||
|
|
|
|||
|
|
| 比例 | 尺寸 |
|
|||
|
|
|------|------|
|
|||
|
|
| 1:1 | 1328×1328 |
|
|||
|
|
| 16:9 | 1664×928 (默认) |
|
|||
|
|
| 9:16 | 928×1664 |
|
|||
|
|
| 4:3 | 1472×1104 |
|
|||
|
|
| 3:4 | 1104×1472 |
|
|||
|
|
|
|||
|
|
## 核心参数
|
|||
|
|
|
|||
|
|
```python
|
|||
|
|
from dashscope import ImageSynthesis
|
|||
|
|
|
|||
|
|
response = ImageSynthesis.call(
|
|||
|
|
api_key="your-api-key",
|
|||
|
|
model="qwen-image-plus",
|
|||
|
|
prompt="你的图像描述",
|
|||
|
|
negative_prompt=" ", # 反向提示词
|
|||
|
|
n=1, # 生成数量
|
|||
|
|
size="1328*1328", # 图像尺寸
|
|||
|
|
prompt_extend=True, # 智能改写 prompt (额外 3-5 秒)
|
|||
|
|
watermark=False, # 是否添加水印
|
|||
|
|
)
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
## 生成效果
|
|||
|
|
|
|||
|
|
| 橘猫下午茶 | 赛博朋克城市 |
|
|||
|
|
|-----------|-------------|
|
|||
|
|
|  |  |
|