qwen-image-2

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Qwen-Image - Alibaba Image Generation

Qwen-Image - 阿里巴巴AI图片生成工具

Generate and edit images with Alibaba Qwen-Image-2.0 models via inference.sh CLI.

通过inference.sh CLI工具，使用阿里巴巴Qwen-Image-2.0模型生成和编辑图片。

Quick Start

快速开始

Requires inference.sh CLI (
infsh
). Get installation instructions:
npx skills add inference-sh/skills@agent-tools

bash

infsh login

infsh app run alibaba/qwen-image-2 --input '{"prompt": "A serene mountain landscape at sunset"}'

需要安装inference.sh CLI（
infsh
）。获取安装指引：
npx skills add inference-sh/skills@agent-tools

bash

infsh login

infsh app run alibaba/qwen-image-2 --input '{"prompt": "A serene mountain landscape at sunset"}'

Models

模型列表

Model	App ID	Speed	Text Rendering	Best For
Qwen-Image-2.0	`alibaba/qwen-image-2`	Fast	Good	General use
Qwen-Image-2.0-Pro	`alibaba/qwen-image-2-pro`	Standard	Professional	Posters, text-heavy designs

模型	应用ID	速度	文字渲染能力	适用场景
Qwen-Image-2.0	`alibaba/qwen-image-2`	快速	良好	通用场景
Qwen-Image-2.0-Pro	`alibaba/qwen-image-2-pro`	标准速度	专业级	海报、文字密集型设计

Search Qwen Image Apps

搜索Qwen Image应用

bash

infsh app list --search "qwen image"

bash

infsh app list --search "qwen image"

Examples

使用示例

Basic Text-to-Image

基础文本转图片

bash

infsh app run alibaba/qwen-image-2 --input '{
  "prompt": "A futuristic cityscape at sunset with flying cars"
}'

bash

infsh app run alibaba/qwen-image-2 --input '{
  "prompt": "A futuristic cityscape at sunset with flying cars"
}'

Multiple Images

生成多张图片

bash

infsh app run alibaba/qwen-image-2 --input '{
  "prompt": "Minimalist logo design for a coffee shop",
  "num_images": 4
}'

bash

infsh app run alibaba/qwen-image-2 --input '{
  "prompt": "Minimalist logo design for a coffee shop",
  "num_images": 4
}'

Custom Resolution

自定义分辨率

bash

infsh app run alibaba/qwen-image-2-pro --input '{
  "prompt": "Panoramic mountain landscape with northern lights",
  "width": 1536,
  "height": 1024
}'

bash

infsh app run alibaba/qwen-image-2-pro --input '{
  "prompt": "Panoramic mountain landscape with northern lights",
  "width": 1536,
  "height": 1024
}'

Text-Heavy Poster (Pro)

文字密集型海报（Pro版）

bash

infsh app run alibaba/qwen-image-2-pro --input '{
  "prompt": "Poster with title \"Summer Sale!\" in bold red text at the top. Subtitle \"50% Off Everything\" in blue below. Beach background with palm trees.",
  "width": 1024,
  "height": 1536,
  "prompt_extend": false
}'

bash

infsh app run alibaba/qwen-image-2-pro --input '{
  "prompt": "Poster with title \"Summer Sale!\" in bold red text at the top. Subtitle \"50% Off Everything\" in blue below. Beach background with palm trees.",
  "width": 1024,
  "height": 1536,
  "prompt_extend": false
}'

Image Editing (Multi-Reference)

多参考图编辑

bash

infsh app run alibaba/qwen-image-2 --input '{
  "prompt": "Make the girl from Image 1 wear the dress from Image 2 in the pose from Image 3",
  "reference_images": [
    {"uri": "https://example.com/person.jpg"},
    {"uri": "https://example.com/dress.jpg"},
    {"uri": "https://example.com/pose.jpg"}
  ]
}'

bash

infsh app run alibaba/qwen-image-2 --input '{
  "prompt": "Make the girl from Image 1 wear the dress from Image 2 in the pose from Image 3",
  "reference_images": [
    {"uri": "https://example.com/person.jpg"},
    {"uri": "https://example.com/dress.jpg"},
    {"uri": "https://example.com/pose.jpg"}
  ]
}'

With Negative Prompt

使用负面提示词

bash

infsh app run alibaba/qwen-image-2-pro --input '{
  "prompt": "Professional headshot portrait, studio lighting",
  "negative_prompt": "low resolution, blurry, deformed, oversaturated"
}'

bash

infsh app run alibaba/qwen-image-2-pro --input '{
  "prompt": "Professional headshot portrait, studio lighting",
  "negative_prompt": "low resolution, blurry, deformed, oversaturated"
}'

Reproducible with Seed

固定随机种子生成可复现图片

bash

infsh app run alibaba/qwen-image-2 --input '{
  "prompt": "Abstract geometric art in blue and gold",
  "seed": 12345
}'

bash

infsh app run alibaba/qwen-image-2 --input '{
  "prompt": "Abstract geometric art in blue and gold",
  "seed": 12345
}'

Input Options

输入参数选项

Parameter	Type	Description
`prompt`	string	Required. What to generate or edit (max 800 chars)
`reference_images`	array	Input images for editing (1-3 images)
`num_images`	integer	Number of images to generate (1-6)
`width`	integer	Output width in pixels (512-2048)
`height`	integer	Output height in pixels (512-2048)
`watermark`	boolean	Add "Qwen-Image" watermark
`negative_prompt`	string	Content to avoid (max 500 chars)
`prompt_extend`	boolean	Enable prompt rewriting (default: true)
`seed`	integer	Random seed for reproducibility (0-2147483647)

Size constraint: Total pixels must be between 512×512 and 2048×2048.

参数	类型	说明
`prompt`	字符串	必填。生成或编辑的内容描述（最多800字符）
`reference_images`	数组	用于编辑的输入图片（1-3张）
`num_images`	整数	生成图片的数量（1-6张）
`width`	整数	输出图片宽度（512-2048像素）
`height`	整数	输出图片高度（512-2048像素）
`watermark`	布尔值	是否添加“Qwen-Image”水印
`negative_prompt`	字符串	需要避免生成的内容（最多500字符）
`prompt_extend`	布尔值	是否启用提示词自动优化（默认：true）
`seed`	整数	用于结果复现的随机种子（0-2147483647）

尺寸限制：总像素范围必须在512×512到2048×2048之间。

Output

输出内容

Field	Type	Description
`images`	array	The generated or edited images (PNG format)
`output_meta`	object	Metadata with dimensions and count

字段	类型	说明
`images`	数组	生成或编辑后的图片（PNG格式）
`output_meta`	对象	包含图片尺寸和数量的元数据

Prompt Tips

提示词技巧

For Text Rendering (use Pro model):

Put exact text in quotes:
```
"Title: \"Hello World!\""
```
Specify font style, color, position
Set
```
prompt_extend: false
```
for precise control

Styles: photorealistic, illustration, watercolor, oil painting, digital art, anime, 3D render

Composition: close-up, wide shot, aerial view, macro, portrait, landscape

Lighting: natural light, studio lighting, golden hour, dramatic shadows, neon

文字渲染技巧（请使用Pro模型）：

将需要精确呈现的文字放在引号中：
```
"Title: \"Hello World!\""
```
明确指定字体样式、颜色和位置
设置
```
prompt_extend: false
```
以实现精确控制

风格选项：写实风格、插画、水彩画、油画、数字艺术、动漫、3D渲染

构图选项：特写、广角、航拍、微距、人像、风景

光线选项：自然光、影棚光、黄金时刻、戏剧性阴影、霓虹灯光

Sample Workflow

典型工作流

bash

undefined

bash

undefined

1. Generate sample input to see all options

1. 生成示例输入以查看所有参数选项

infsh app sample alibaba/qwen-image-2-pro --save input.json

2. Edit the prompt

2. 编辑提示词

3. Run

3. 运行命令

infsh app run alibaba/qwen-image-2-pro --input input.json

undefined

infsh app run alibaba/qwen-image-2-pro --input input.json

undefined

Model Comparison

模型对比

Feature	qwen-image-2	qwen-image-2-pro
Speed	Faster	Standard
Text Rendering	Good	Professional
Realism	Standard	Fine-grained
Semantic Adherence	Good	Enhanced

特性	qwen-image-2	qwen-image-2-pro
速度	更快	标准速度
文字渲染	良好	专业级
真实感	标准	精细化
语义贴合度	良好	增强版

Related Skills

Full platform skill (all 150+ apps)

全平台技能（包含150+应用）

npx skills add inference-sh/skills@agent-tools

All image generation models

所有AI图片生成模型

npx skills add inference-sh/skills@ai-image-generation

Video generation (for image-to-video)

AI视频生成（用于图片转视频）

npx skills add inference-sh/skills@ai-video-generation


Browse all image apps: `infsh app list --category image`

npx skills add inference-sh/skills@ai-video-generation


浏览所有图片类应用：`infsh app list --category image`

Documentation

官方文档

Running Apps - How to run apps via CLI
Streaming Results - Real-time progress updates
File Handling - Working with images

运行应用 - 如何通过CLI运行应用
流式结果 - 实时进度更新
文件处理](https://inference.sh/docs/api/sdk/files) - 图片文件操作指南

qwen-image-2

Original

Translation

Qwen-Image - Alibaba Image Generation

Qwen-Image - 阿里巴巴AI图片生成工具

Quick Start

快速开始

Models

模型列表

Search Qwen Image Apps

搜索Qwen Image应用

Examples

使用示例

Basic Text-to-Image

基础文本转图片

Multiple Images

生成多张图片

Custom Resolution

自定义分辨率

Text-Heavy Poster (Pro)

文字密集型海报（Pro版）

Image Editing (Multi-Reference)

多参考图编辑

With Negative Prompt

使用负面提示词

Reproducible with Seed

固定随机种子生成可复现图片

Input Options

输入参数选项

Output

输出内容

Prompt Tips

提示词技巧

Sample Workflow

典型工作流

1. Generate sample input to see all options

1. 生成示例输入以查看所有参数选项

2. Edit the prompt

2. 编辑提示词

3. Run

3. 运行命令

Model Comparison

模型对比

Related Skills

相关技能

Full platform skill (all 150+ apps)

全平台技能（包含150+应用）

All image generation models

所有AI图片生成模型

Video generation (for image-to-video)

AI视频生成（用于图片转视频）

Documentation

官方文档