Loading...
qwen-image-2-pro
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseQwen-Image Pro - Professional Image Generation
Qwen-Image Pro - 专业图片生成
Generate images with Alibaba Qwen-Image-2.0-Pro via inference.sh CLI. Best for professional text rendering and complex designs.
通过inference.sh CLI调用Alibaba Qwen-Image-2.0-Pro生成图片，非常适合专业文本渲染和复杂设计场景。
Quick Start
快速开始
Requires inference.sh CLI (). Get installation instructions:infshnpx skills add inference-sh/skills@agent-tools
bash
infsh login
infsh app run alibaba/qwen-image-2-pro --input '{"prompt": "Poster with title \"Welcome!\" in bold blue text"}'需要安装inference.sh CLI（）。获取安装指引：infshnpx skills add inference-sh/skills@agent-tools
bash
infsh login
infsh app run alibaba/qwen-image-2-pro --input '{"prompt": "Poster with title \"Welcome!\" in bold blue text"}'Pro Model Capabilities
Pro版本模型能力
- Professional Text Rendering: Multi-line and paragraph-level text with fine-grained detail
- Fine-grained Realism: Better textures and photorealistic scenes
- Stronger Semantic Adherence: More accurately follows complex prompts
- Complex Designs: Ideal for text + image combinations
- 专业文本渲染：支持多行及段落级文本，细节精细
- 精细粒度写实：纹理表现更出色，场景贴近真实
- 更强语义贴合：更精准地遵循复杂提示词要求
- 复杂设计适配：非常适合图文结合的设计场景
Examples
示例
Basic Text-to-Image
基础文本转图片
bash
infsh app run alibaba/qwen-image-2-pro --input '{
"prompt": "A futuristic cityscape at sunset with flying cars"
}'bash
infsh app run alibaba/qwen-image-2-pro --input '{
"prompt": "A futuristic cityscape at sunset with flying cars"
}'Text-Heavy Poster
文字密集型海报
bash
infsh app run alibaba/qwen-image-2-pro --input '{
"prompt": "Healing-style hand-drawn poster featuring three puppies playing with a ball. The main title \"Come Play Ball!\" is prominently displayed at the top in bold, blue cartoon font. Below, the subtitle \"Join the Fun!\" appears in green font.",
"width": 1024,
"height": 1536,
"prompt_extend": false
}'bash
infsh app run alibaba/qwen-image-2-pro --input '{
"prompt": "Healing-style hand-drawn poster featuring three puppies playing with a ball. The main title \"Come Play Ball!\" is prominently displayed at the top in bold, blue cartoon font. Below, the subtitle \"Join the Fun!\" appears in green font.",
"width": 1024,
"height": 1536,
"prompt_extend": false
}'Marketing Banner
营销横幅
bash
infsh app run alibaba/qwen-image-2-pro --input '{
"prompt": "Professional marketing banner for summer sale. Large text \"SUMMER SALE\" in white on gradient sunset background. \"50% OFF\" in yellow below. Clean, modern design.",
"width": 1920,
"height": 1080,
"prompt_extend": false,
"negative_prompt": "blurry text, distorted text, low quality"
}'bash
infsh app run alibaba/qwen-image-2-pro --input '{
"prompt": "Professional marketing banner for summer sale. Large text \"SUMMER SALE\" in white on gradient sunset background. \"50% OFF\" in yellow below. Clean, modern design.",
"width": 1920,
"height": 1080,
"prompt_extend": false,
"negative_prompt": "blurry text, distorted text, low quality"
}'Multiple Variations
多版本生成
bash
infsh app run alibaba/qwen-image-2-pro --input '{
"prompt": "Minimalist logo design for a coffee shop called \"Bean & Brew\"",
"num_images": 4
}'bash
infsh app run alibaba/qwen-image-2-pro --input '{
"prompt": "Minimalist logo design for a coffee shop called \"Bean & Brew\"",
"num_images": 4
}'Image Editing (Style Transfer)
图片编辑（风格迁移）
bash
infsh app run alibaba/qwen-image-2-pro --input '{
"prompt": "Make the person from Image 1 wear the outfit from Image 2",
"reference_images": [
{"uri": "https://example.com/person.jpg"},
{"uri": "https://example.com/outfit.jpg"}
],
"num_images": 2
}'bash
infsh app run alibaba/qwen-image-2-pro --input '{
"prompt": "Make the person from Image 1 wear the outfit from Image 2",
"reference_images": [
{"uri": "https://example.com/person.jpg"},
{"uri": "https://example.com/outfit.jpg"}
],
"num_images": 2
}'Reproducible Generation
可复现生成
bash
infsh app run alibaba/qwen-image-2-pro --input '{
"prompt": "Abstract geometric art in blue and gold",
"seed": 12345
}'bash
infsh app run alibaba/qwen-image-2-pro --input '{
"prompt": "Abstract geometric art in blue and gold",
"seed": 12345
}'Input Options
输入参数选项
| Parameter | Type | Description |
|---|---|---|
| string | Required. What to generate or edit (max 800 chars) |
| array | Input images for editing (1-3 images) |
| integer | Number of images to generate (1-6) |
| integer | Output width in pixels (512-2048) |
| integer | Output height in pixels (512-2048) |
| boolean | Add "Qwen-Image" watermark |
| string | Content to avoid (max 500 chars) |
| boolean | Enable prompt rewriting (default: true) |
| integer | Random seed for reproducibility (0-2147483647) |
Size constraint: Total pixels must be between 512×512 and 2048×2048.
| 参数 | 类型 | 描述 |
|---|---|---|
| string | 必填。要生成或编辑的内容（最多800字符） |
| array | 用于编辑的输入图片（1-3张） |
| integer | 生成图片数量（1-6张） |
| integer | 输出图片宽度（像素，范围512-2048） |
| integer | 输出图片高度（像素，范围512-2048） |
| boolean | 是否添加“Qwen-Image”水印 |
| string | 要避免生成的内容（最多500字符） |
| boolean | 是否启用提示词重写（默认值：true） |
| integer | 用于结果复现的随机种子（范围0-2147483647） |
尺寸限制：总像素数需在512×512到2048×2048之间。
Output
输出内容
| Field | Type | Description |
|---|---|---|
| array | The generated or edited images (PNG format) |
| object | Metadata with dimensions and count |
| 字段 | 类型 | 描述 |
|---|---|---|
| array | 生成或编辑后的图片（PNG格式） |
| object | 包含尺寸、数量等信息的元数据 |
Text Rendering Tips
文本渲染技巧
For best text results with the Pro model:
- Use quotes around exact text:
"Title: \"Hello World!\"" - Specify font details: color, style, size, position
- Disable prompt_extend: Set for precise control
prompt_extend: false - Use negative prompts:
"blurry text, distorted text, low quality"
Example prompt structure:
Poster with the title "GRAND OPENING" in large red serif font at the top center.
Below, the date "March 15, 2024" in smaller black text.
Background: elegant gold and white gradient.
Style: professional, clean, modern.为了获得最佳的文本渲染效果，使用Pro版本模型时请遵循以下建议：
- 为精确文本添加引号：例如
"Title: \"Hello World!\"" - 指定字体细节：包括颜色、样式、大小、位置
- 关闭prompt_extend：设置以获得精确控制
prompt_extend: false - 使用负面提示词：例如
"blurry text, distorted text, low quality"
提示词结构示例：
Poster with the title "GRAND OPENING" in large red serif font at the top center.
Below, the date "March 15, 2024" in smaller black text.
Background: elegant gold and white gradient.
Style: professional, clean, modern.Recommended Negative Prompt
推荐负面提示词
json
{
"negative_prompt": "low resolution, low quality, deformed limbs, deformed fingers, oversaturated, waxy, no facial details, overly smooth, AI-like, chaotic composition, blurry text, distorted text"
}json
{
"negative_prompt": "low resolution, low quality, deformed limbs, deformed fingers, oversaturated, waxy, no facial details, overly smooth, AI-like, chaotic composition, blurry text, distorted text"
}Sample Workflow
示例工作流
bash
undefinedbash
undefined1. Generate sample input to see all options
1. 生成示例输入以查看所有可选参数
infsh app sample alibaba/qwen-image-2-pro --save input.json
infsh app sample alibaba/qwen-image-2-pro --save input.json
2. Edit the prompt
2. 编辑提示词
3. Run
3. 执行生成
infsh app run alibaba/qwen-image-2-pro --input input.json
undefinedinfsh app run alibaba/qwen-image-2-pro --input input.json
undefinedPython SDK
Python SDK
python
from inferencesh import inference
client = inference()python
from inferencesh import inference
client = inference()Text-heavy poster
文字密集型海报生成
result = client.run({
"app": "alibaba/qwen-image-2-pro",
"input": {
"prompt": "Poster with title "Welcome!" in bold blue text at top",
"width": 1024,
"height": 1536,
"prompt_extend": False
}
})
print(result["output"])
result = client.run({
"app": "alibaba/qwen-image-2-pro",
"input": {
"prompt": "Poster with title "Welcome!" in bold blue text at top",
"width": 1024,
"height": 1536,
"prompt_extend": False
}
})
print(result["output"])
Stream live updates
流式获取实时更新
for update in client.run({
"app": "alibaba/qwen-image-2-pro",
"input": {
"prompt": "Professional product photography of a watch"
}
}, stream=True):
if update.get("progress"):
print(f"progress: {update['progress']}%")
if update.get("output"):
print(f"output: {update['output']}")
undefinedfor update in client.run({
"app": "alibaba/qwen-image-2-pro",
"input": {
"prompt": "Professional product photography of a watch"
}
}, stream=True):
if update.get("progress"):
print(f"progress: {update['progress']}%")
if update.get("output"):
print(f"output: {update['output']}")
undefinedRelated Skills
相关技能
bash
undefinedbash
undefinedStandard Qwen-Image (faster, general use)
标准版Qwen-Image（速度更快，适合通用场景）
npx skills add inference-sh/skills@qwen-image
npx skills add inference-sh/skills@qwen-image
Full platform skill (all 150+ apps)
全平台技能（包含150+应用）
npx skills add inference-sh/skills@agent-tools
npx skills add inference-sh/skills@agent-tools
All image generation models
所有图片生成模型
npx skills add inference-sh/skills@ai-image-generation
Browse all image apps: `infsh app list --category image`npx skills add inference-sh/skills@ai-image-generation
浏览所有图片类应用：`infsh app list --category image`Documentation
文档链接
- Running Apps - How to run apps via CLI
- Streaming Results - Real-time progress updates
- File Handling - Working with images