imagencn

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

imagencn - Multi-Cloud Text-to-Image Skill

imagencn - 多云平台文本转图像Skill

Overview

概述

imagencn — Image Generation, Cloud-Native: one CLI, every image cloud. The project started with China-friendly clouds and now covers international providers as well.

Generate images using Alibaba Cloud Bailian API. Default endpoint is China region.

Supports six platforms across ten model families:

Alibaba Cloud Bailian (DashScope): Qwen-Image 2.0, Qwen-Image Edit, Qwen-Image legacy, Wan Series, Z-Image
ByteDance Volcano Ark: Doubao-Seedream series (OpenAI-compatible REST)
Tencent Hunyuan: Hunyuan Image 3.0 (OpenAI-compatible REST)
Zhipu / BigModel: CogView-4 and GLM-Image (OpenAI-compatible REST)
StepFun / 阶跃星辰: Step-2X and Step-Image-Edit (OpenAI-compatible REST)
Google Gemini (international): Gemini 3 Pro Image (generateContent REST)

Cross-platform support: Windows, macOS, Linux

imagencn — 图像生成，云原生：一个CLI，对接所有图像云服务。该项目最初面向国内云平台开发，目前已覆盖国际服务商。

可通过阿里云百炼API生成图像。默认接入国内区域端点。

支持6大平台的10个模型系列：

阿里云百炼（DashScope）：Qwen-Image 2.0、Qwen-Image Edit、Qwen-Image legacy、万相系列、Z-Image
字节跳动火山方舟（Volcano Ark）：豆包-Seedream系列（兼容OpenAI REST接口）
腾讯混元（Hunyuan）：混元图像3.0（兼容OpenAI REST接口）
智谱（Zhipu）/ BigModel：CogView-4和GLM-Image（兼容OpenAI REST接口）
阶跃星辰（StepFun）：Step-2X和Step-Image-Edit（兼容OpenAI REST接口）
Google Gemini（国际版）：Gemini 3 Pro Image（generateContent REST接口）

跨平台支持：Windows、macOS、Linux

When to Use This Skill

使用场景

Automatically activate this skill when:

User requests image generation with Chinese text or calligraphy
Need photorealistic images or photography-style visuals
Creating commercial posters, illustrations, or digital art
User mentions any of these: Alibaba Cloud / Bailian / Qwen / Wan / DashScope, ByteDance / Volcano Ark / Seedream / Doubao, Tencent / Hunyuan, Google / Gemini / Nano Banana
User wants an international (non-China) image provider — use the Gemini platform
Any task where AI-generated image with strong Chinese support would be helpful

满足以下任一条件时自动激活该Skill：

用户请求生成包含中文文本或书法的图像
需要写实风格图像或摄影级视觉效果
制作商业海报、插画或数字艺术作品
用户提及以下任一平台：阿里云/百炼/Qwen/万相/DashScope、字节跳动/火山方舟/Seedream/豆包、腾讯/混元、Google/Gemini/Nano Banana
用户需要国际（非国内）图像生成服务商——使用Gemini平台
任何需要强中文支持的AI图像生成任务

Model Reference

模型参考

When the user wants to compare models, check pricing, or browse options before choosing, open the local model reference page in their browser:

bash

open ~/.claude/skills/imagencn/docs/models.html

This page shows all 31 models across 6 platforms with pricing, resolution, feature highlights, and a quick-reference guide. On Linux use

xdg-open

; the file also works from

file://

with no server needed.

当用户需要对比模型、查看定价或选择模型时，在浏览器中打开本地模型参考页面：

bash

open ~/.claude/skills/imagencn/docs/models.html

该页面展示了6大平台的31个模型，包含定价、分辨率、功能亮点及快速参考指南。Linux系统使用

xdg-open

；该文件可通过

file://

协议直接打开，无需服务器。

Workflow

工作流程

Step 1 — Refine the prompt (interactive, never skip)

步骤1 — 优化提示词（交互式，不可跳过）

Users often give short, casual descriptions ("生成一只猫"). Before calling the API, present 3 refined prompt options with different style directions. Add, as appropriate:

Subject details (shape, colour, material, expression, pose)
Lighting (golden hour, studio, rim light, soft diffused, neon, cinematic)
Composition (rule of thirds, shallow depth of field, wide shot, close-up)
Style / medium (photorealistic, oil painting, watercolour, 3D render, vector)
Mood / atmosphere (serene, dramatic, whimsical, dystopian, elegant)
Quality keywords (8K, hyperdetailed, award-winning, professional photography)
For Chinese text on images: text content, placement, font style, colour, size

Label the options clearly (e.g. A / B / C) with a one-line summary of each direction. Let the user pick one, combine elements from multiple, or request a new direction. Iterate until they confirm ("go", "generate", "ok", etc.), then proceed to generation.

用户通常会给出简短、随意的描述（如"生成一只猫"）。调用API前，提供3个不同风格方向的优化提示词选项，可根据需要添加以下元素：

主体细节（形状、颜色、材质、表情、姿态）
光线效果（黄金时段、影棚光、轮廓光、柔和漫射光、霓虹光、电影级光线）
构图方式（三分法、浅景深、广角镜头、特写）
风格/媒介（写实风格、油画、水彩、3D渲染、矢量图）
氛围/情绪（宁静、戏剧性、奇幻、反乌托邦、优雅）
画质关键词（8K、超精细、获奖作品、专业摄影）
图像中的中文文本：文本内容、位置、字体风格、颜色、尺寸

为每个选项添加清晰标签（如A/B/C）及一行风格方向总结。让用户选择其中一个、组合多个选项的元素，或要求新的方向。迭代直到用户确认（如"开始"、"生成"、"ok"等），再进入生成环节。

Step 2 — Pick a model

步骤2 — 选择模型

Choose based on the request (see Model Selection Guide below). Default to

qwen-image-2.0-pro

if unsure. Mention your choice to the user.

根据请求选择模型（参考下方模型选择指南）。若不确定，默认使用

qwen-image-2.0-pro

。向用户说明你的选择。

Step 3 — Pick a size

步骤3 — 选择尺寸

Native 2K for Qwen-Image 2.0,

1K

2K

4K

for Wan2.7, or an aspect-ratio preset (

16:9

1:1

, etc.).

Qwen-Image 2.0默认原生2K；万相2.7支持

1K

2K

4K

；或使用宽高比预设（

16:9

、

1:1

等）。

Step 4 — Generate

步骤4 — 生成图像

Run

scripts/generate_image.py

with the confirmed prompt and output path.

运行

scripts/generate_image.py

，传入确认后的提示词和输出路径。

Step 5 — Save

步骤5 — 保存图像

If the output path was implicit, save into the user's current working directory.

若输出路径未明确指定，保存到用户当前工作目录。

Models

模型详情

Qwen-Image 2.0 family - Latest Flagship (MultiModalConversation API)

Qwen-Image 2.0系列 - 最新旗舰模型（MultiModalConversation API）

Model	Description
`qwen-image-2.0-pro`	Default. Latest flagship, native 2K, strongest typography and detail
`qwen-image-2.0-pro-2026-06-22`	Latest snapshot (Jun 2026): generation + editing fusion, better text rendering and prompt adherence
`qwen-image-2.0`	Standard 2.0 tier, native 2K
`qwen-image-max`	Previous-gen flagship (Dec 2025)
`qwen-image-max-2025-12-30`	qwen-image-max snapshot: improved realism, fewer AI artifacts

模型	描述
`qwen-image-2.0-pro`	默认模型。最新旗舰版，原生2K分辨率，文本渲染和细节表现最强
`qwen-image-2.0-pro-2026-06-22`	最新快照版本（2026年6月）：融合生成与编辑功能，文本渲染和提示词遵循度更优
`qwen-image-2.0`	标准2.0版本，原生2K分辨率
`qwen-image-max`	上一代旗舰模型（2025年12月）
`qwen-image-max-2025-12-30`	qwen-image-max快照版本：写实度提升，AI伪影减少

Qwen-Image Edit family - Image Editing (MultiModalConversation API)

Qwen-Image Edit系列 - 图像编辑模型（MultiModalConversation API）

Editing models require an input image via

--image

(local path or URL). Omit

--size

to match the input image dimensions.

Model	Description
`qwen-image-edit-max`	Flagship editing model, strongest instruction following
`qwen-image-edit-max-2026-01-16`	Latest max snapshot (Jan 2026)
`qwen-image-edit-plus`	Faster, lower-cost editing

编辑模型需通过

--image

参数传入输入图像（本地路径或URL）。省略

--size

参数将匹配输入图像尺寸。

模型	描述
`qwen-image-edit-max`	旗舰编辑模型，指令遵循度最强
`qwen-image-edit-max-2026-01-16`	最新max快照版本（2026年1月）
`qwen-image-edit-plus`	更快、低成本的编辑模型

Qwen-Image legacy (ImageSynthesis API)

Qwen-Image legacy（ImageSynthesis API）

Model	Description
`qwen-image-plus`	Distilled accelerated version of qwen-image-max
`qwen-image-plus-2026-01-09`	qwen-image-plus snapshot (Jan 2026): faster high-quality generation
`qwen-image`	Base model

模型	描述
`qwen-image-plus`	qwen-image-max的蒸馏加速版本
`qwen-image-plus-2026-01-09`	qwen-image-plus快照版本（2026年1月）：更快生成高质量图像
`qwen-image`	基础模型

Wan Series - Photorealistic Generation (ImageGeneration API)

万相系列 - 写实风格生成模型（ImageGeneration API）

Model	Description
`wan2.7-image-pro`	Latest. Up to 4K output, unified architecture (T2I + edit + multi-image)
`wan2.7-image`	Wan 2.7 standard, up to 2K
`wan2.6-t2i`	Wan 2.6, flexible sizing
`wan2.5-t2i-preview`	High quality, up to 768x2700
`wan2.2-t2i-flash`	Speed-optimized
`wan2.2-t2i-plus`	Professional tier
`wanx2.1-t2i-turbo`	Fast execution
`wanx2.1-t2i-plus`	Professional tier
`wanx2.0-t2i-turbo`	Earlier generation

模型	描述
`wan2.7-image-pro`	最新版本。最高支持4K输出，统一架构（文本转图像+编辑+多图像）
`wan2.7-image`	万相2.7标准版，最高支持2K
`wan2.6-t2i`	万相2.6，尺寸灵活
`wan2.5-t2i-preview`	高质量，最高支持768x2700
`wan2.2-t2i-flash`	速度优化版本
`wan2.2-t2i-plus`	专业版
`wanx2.1-t2i-turbo`	快速执行版本
`wanx2.1-t2i-plus`	专业版
`wanx2.0-t2i-turbo`	早期版本

Z-Image - Lightweight & Fast (MultiModalConversation API)

Z-Image - 轻量快速模型（MultiModalConversation API）

Model	Description
`z-image-turbo`	Fast, low-cost generation; bilingual (CN/EN) text rendering, high-fidelity portraits and product images. Pixel area 512x512 to 2048x2048

模型	描述
`z-image-turbo`	快速、低成本生成；支持中英双语文本渲染，人像和产品图像保真度高。像素范围512x512至2048x2048

Volcano Ark - ByteDance Seedream (OpenAI-compatible API)

火山方舟 - 字节跳动Seedream（兼容OpenAI API）

Model	Description
`doubao-seedream-5-0-260128`	Ark default. Latest, up to 3K, PNG/JPEG output, best text rendering
`doubao-seedream-4-5-251128`	Seedream 4.5, up to 4K
`doubao-seedream-4-0-250828`	Seedream 4.0, up to 4K, budget-friendly

模型	描述
`doubao-seedream-5-0-260128`	方舟默认模型。最新版本，最高支持3K，输出PNG/JPEG格式，文本渲染效果最佳
`doubao-seedream-4-5-251128`	Seedream 4.5，最高支持4K
`doubao-seedream-4-0-250828`	Seedream 4.0，最高支持4K，性价比高

Tencent Hunyuan (OpenAI-compatible API)

腾讯混元（兼容OpenAI API）

Model	Description
`hy-image-v3.0`	Hunyuan default. Flagship 3.0, strong composition awareness, handles complex Chinese prompts up to 8K chars

模型	描述
`hy-image-v3.0`	混元默认模型。旗舰3.0版本，构图感知能力强，支持最长8000字符的复杂中文提示词

Zhipu / BigModel - CogView-4 & GLM-Image (OpenAI-compatible API)

智谱（Zhipu）/ BigModel - CogView-4 & GLM-Image（兼容OpenAI API）

Model	Description
`cogview-4`	Zhipu default. Stable alias for latest CogView-4, native Chinese text rendering
`cogview-4-250304`	CogView-4 fixed snapshot (Mar 2025), reproducible results
`glm-image`	GLM-Image flagship, up to 2048x2048, hybrid autoregressive/diffusion

模型	描述
`cogview-4`	智谱默认模型。CogView-4最新版本的稳定别名，原生支持中文文本渲染
`cogview-4-250304`	CogView-4固定快照版本（2025年3月），结果可复现
`glm-image`	GLM-Image旗舰模型，最高支持2048x2048，混合自回归/扩散架构

StepFun / 阶跃星辰 - Step-2X (OpenAI-compatible API)

阶跃星辰（StepFun）- Step-2X（兼容OpenAI API）

Model	Description
`step-2x-large`	StepFun default. High quality (0.1 RMB/image), up to 1024x1024
`step-image-edit-2`	Fast & cheap (0.02 RMB/image), supports negative prompts, 8 inference steps

模型	描述
`step-2x-large`	阶跃星辰默认模型。高质量（0.1元/张），最高支持1024x1024
`step-image-edit-2`	快速低成本（0.02元/张），支持负提示词，8步推理

Google Gemini - International (generateContent API)

Google Gemini（国际版）（generateContent API）

Model	Description
`gemini-3-pro-image-preview`	Gemini default. Google flagship image model, 512/1K/2K named sizes plus aspect-ratio presets

模型	描述
`gemini-3-pro-image-preview`	Gemini默认模型。Google旗舰图像模型，支持512/1K/2K命名尺寸及宽高比预设

Usage

使用方法

Basic Usage

基础用法

bash

undefined

bash

undefined

Default model (qwen-image-2.0-pro, native 2K output)

默认模型（qwen-image-2.0-pro，原生2K输出）

python ~/.claude/skills/imagencn/scripts/generate_image.py "A cute cat" output.png

python ~/.claude/skills/imagencn/scripts/generate_image.py "一只可爱的猫" output.png

Photorealistic with Wan model (Wan2.7 supports 4K)

使用万相模型生成写实风格图像（万相2.7支持4K）

python ~/.claude/skills/imagencn/scripts/generate_image.py --model wan2.7-image-pro --size 4K "Realistic photo of mountains at sunset" photo.png

python ~/.claude/skills/imagencn/scripts/generate_image.py --model wan2.7-image-pro --size 4K "日落时分的写实山脉照片" photo.png

Edit an existing image (requires --image; local path or URL)

编辑现有图像（需--image参数；本地路径或URL）

python ~/.claude/skills/imagencn/scripts/generate_image.py --model qwen-image-edit-max --image input.png "Change the background to a beach at sunset" edited.png

undefined

python ~/.claude/skills/imagencn/scripts/generate_image.py --model qwen-image-edit-max --image input.png "将背景改为日落时分的海滩" edited.png

undefined

Size Options

尺寸选项

bash

undefined

bash

undefined

Use ratio preset

使用宽高比预设

python ~/.claude/skills/imagencn/scripts/generate_image.py --size 16:9 "Wide landscape" landscape.png

python ~/.claude/skills/imagencn/scripts/generate_image.py --size 16:9 "宽幅风景" landscape.png

Use exact dimensions

使用精确尺寸

python ~/.claude/skills/imagencn/scripts/generate_image.py --size 1280*720 "Custom size" custom.png

undefined

python ~/.claude/skills/imagencn/scripts/generate_image.py --size 1280*720 "自定义尺寸" custom.png

undefined

Size Presets

尺寸预设

Qwen-Image 2.0 (native 2K):

```
1:1
```
-> 2048x2048 (default)
```
16:9
```
-> 2688x1536
```
9:16
```
-> 1536x2688
```
4:3
```
-> 2304x1728
```
3:4
```
-> 1728x2304
```
1K
```
-> 1024x1024
```
2K
```
-> 2048x2048

Qwen-Image legacy:

```
1:1
```
-> 1328x1328
```
16:9
```
-> 1664x928
```
9:16
```
-> 928x1664
```
4:3
```
-> 1472x1104
```
3:4
```
-> 1104x1472

Z-Image (pixel area 512x512 to 2048x2048):

```
1:1
```
-> 1024x1024 (default)
```
16:9
```
-> 1280x720
```
9:16
```
-> 720x1280
```
2:3
```
-> 1024x1536
```
3:2
```
-> 1536x1024
```
1K
```
-> 1024x1024

Wan Series (Wan2.7 also accepts
1K
/
2K
/
4K
):

```
1:1
```
-> 1024x1024
```
1:1-large
```
-> 1280x1280
```
16:9
```
-> 1280x720
```
9:16
```
-> 720x1280
```
4:3
```
-> 1200x900
```
3:4
```
-> 900x1200
```
2:1
```
-> 1440x720

Volcano Ark (Seedream):

```
1:1
```
-> 2048x2048
```
16:9
```
-> 2848x1600
```
9:16
```
-> 1600x2848
```
4:3
```
-> 2304x1728
```
3:4
```
-> 1728x2304
```
3:2
```
-> 2496x1664
```
2:3
```
-> 1664x2496
```
1K
```
/
```
2K
```
/
```
3K
```
/
```
4K
```
(model-dependent max resolution)

Tencent Hunyuan (colon-separated format):

```
1:1
```
-> 1024:1024
```
16:9
```
-> 1920:1080
```
9:16
```
-> 1080:1920
```
4:3
```
-> 1600:1200
```
3:4
```
-> 1200:1600

Zhipu (CogView-4 / GLM-Image):

```
1:1
```
-> 1024x1024 (default)
```
16:9
```
-> 1344x768
```
9:16
```
-> 768x1344
```
4:3
```
-> 1152x864
```
3:4
```
-> 864x1152
```
2:1
```
-> 1440x720
```
1:2
```
-> 720x1440

StepFun (Step-2X):

```
1:1
```
-> 1024x1024 (default)
```
1:1-small
```
-> 512x512
```
16:9
```
-> 1280x800
```
9:16
```
-> 800x1280

Google Gemini (named sizes + aspect ratios):

```
512
```
/
```
1K
```
(default) /
```
2K
```
-> named output size
```
1:1
```
,
```
16:9
```
,
```
9:16
```
,
```
4:3
```
,
```
3:4
```
-> aspect ratio (no exact pixel sizes)

Qwen-Image 2.0（原生2K）：

```
1:1
```
-> 2048x2048（默认）
```
16:9
```
-> 2688x1536
```
9:16
```
-> 1536x2688
```
4:3
```
-> 2304x1728
```
3:4
```
-> 1728x2304
```
1K
```
-> 1024x1024
```
2K
```
-> 2048x2048

Qwen-Image legacy：

```
1:1
```
-> 1328x1328
```
16:9
```
-> 1664x928
```
9:16
```
-> 928x1664
```
4:3
```
-> 1472x1104
```
3:4
```
-> 1104x1472

Z-Image（像素范围512x512至2048x2048）：

```
1:1
```
-> 1024x1024（默认）
```
16:9
```
-> 1280x720
```
9:16
```
-> 720x1280
```
2:3
```
-> 1024x1536
```
3:2
```
-> 1536x1024
```
1K
```
-> 1024x1024

万相系列（万相2.7还支持
1K
/
2K
/
4K
）：

```
1:1
```
-> 1024x1024
```
1:1-large
```
-> 1280x1280
```
16:9
```
-> 1280x720
```
9:16
```
-> 720x1280
```
4:3
```
-> 1200x900
```
3:4
```
-> 900x1200
```
2:1
```
-> 1440x720

火山方舟（Seedream）：

```
1:1
```
-> 2048x2048
```
16:9
```
-> 2848x1600
```
9:16
```
-> 1600x2848
```
4:3
```
-> 2304x1728
```
3:4
```
-> 1728x2304
```
3:2
```
-> 2496x1664
```
2:3
```
-> 1664x2496
```
1K
```
/
```
2K
```
/
```
3K
```
/
```
4K
```
（取决于模型支持的最大分辨率）

腾讯混元（冒号分隔格式）：

```
1:1
```
-> 1024:1024
```
16:9
```
-> 1920:1080
```
9:16
```
-> 1080:1920
```
4:3
```
-> 1600:1200
```
3:4
```
-> 1200:1600

智谱（CogView-4 / GLM-Image）：

```
1:1
```
-> 1024x1024（默认）
```
16:9
```
-> 1344x768
```
9:16
```
-> 768x1344
```
4:3
```
-> 1152x864
```
3:4
```
-> 864x1152
```
2:1
```
-> 1440x720
```
1:2
```
-> 720x1440

阶跃星辰（Step-2X）：

```
1:1
```
-> 1024x1024（默认）
```
1:1-small
```
-> 512x512
```
16:9
```
-> 1280x800
```
9:16
```
-> 800x1280

Google Gemini（命名尺寸+宽高比）：

```
512
```
/
```
1K
```
（默认） /
```
2K
```
-> 命名输出尺寸
```
1:1
```
,
```
16:9
```
,
```
9:16
```
,
```
4:3
```
,
```
3:4
```
-> 宽高比（无精确像素尺寸）

Advanced Options

高级选项

bash

undefined

bash

undefined

With negative prompt

使用负提示词

python ~/.claude/skills/imagencn/scripts/generate_image.py --negative "blurry, low quality" "High quality portrait" portrait.png

python ~/.claude/skills/imagencn/scripts/generate_image.py --negative "模糊, 低画质" "高质量人像" portrait.png

Disable automatic prompt extension (DashScope only)

禁用自动提示词扩展（仅DashScope支持）

python ~/.claude/skills/imagencn/scripts/generate_image.py --no-extend "A photorealistic cat" cat.png

python ~/.claude/skills/imagencn/scripts/generate_image.py --no-extend "写实风格的猫" cat.png

Set random seed for reproducibility

设置随机种子以复现结果

python ~/.claude/skills/imagencn/scripts/generate_image.py --seed 42 "A cat" cat.png

python ~/.claude/skills/imagencn/scripts/generate_image.py --seed 42 "一只猫" cat.png

Guidance scale (Volcano Ark only)

设置引导尺度（仅火山方舟支持）

python ~/.claude/skills/imagencn/scripts/generate_image.py --platform ark --guidance-scale 7.5 "Portrait" portrait.png

python ~/.claude/skills/imagencn/scripts/generate_image.py --platform ark --guidance-scale 7.5 "人像" portrait.png

Disable watermark (Volcano Ark only)

禁用水印（仅火山方舟支持）

python ~/.claude/skills/imagencn/scripts/generate_image.py --platform ark --no-watermark "Artwork" art.png

python ~/.claude/skills/imagencn/scripts/generate_image.py --platform ark --no-watermark "艺术作品" art.png

Auto-enhance prompt on/off (Tencent Hunyuan only, --revise 0=off 1=on)

开启/关闭提示词自动优化（仅腾讯混元支持，--revise 0=关闭 1=开启）

python ~/.claude/skills/imagencn/scripts/generate_image.py --platform hunyuan --revise 0 "A cat" cat.png

python ~/.claude/skills/imagencn/scripts/generate_image.py --platform hunyuan --revise 0 "一只猫" cat.png

Add AI logo (Tencent Hunyuan only, --logo 0=no 1=yes)

添加AI标识（仅腾讯混元支持，--logo 0=不添加 1=添加）

python ~/.claude/skills/imagencn/scripts/generate_image.py --platform hunyuan --logo 1 "Poster" poster.png

python ~/.claude/skills/imagencn/scripts/generate_image.py --platform hunyuan --logo 1 "海报" poster.png

Dry run (preview without making API call)

试运行（预览但不调用API）

python ~/.claude/skills/imagencn/scripts/generate_image.py --dry-run --platform ark "Test prompt"

python ~/.claude/skills/imagencn/scripts/generate_image.py --dry-run --platform ark "测试提示词"

List all models

列出所有模型

python ~/.claude/skills/imagencn/scripts/generate_image.py --list-models

undefined

python ~/.claude/skills/imagencn/scripts/generate_image.py --list-models

undefined

Requirements

依赖要求

bash

pip install dashscope requests

bash

pip install dashscope requests

Optional: for coloured output and styled tables

可选：用于彩色输出和样式化表格

pip install rich

undefined

pip install rich

undefined

Environment Variables

环境变量

bash

undefined

bash

undefined

Alibaba Cloud Bailian (DashScope)

阿里云百炼（DashScope）

export DASHSCOPE_API_KEY="your_api_key" # Required export DASHSCOPE_MODEL="wan2.7-image-pro" # Optional default model export DASHSCOPE_API_BASE="cn" # Optional: cn, sg, us

export DASHSCOPE_API_KEY="your_api_key" # 必填 export DASHSCOPE_MODEL="wan2.7-image-pro" # 可选：默认模型 export DASHSCOPE_API_BASE="cn" # 可选：cn, sg, us

ByteDance Volcano Ark

字节跳动火山方舟

export ARK_API_KEY="your_api_key" # Required for Ark export ARK_MODEL="doubao-seedream-5-0-260128" # Optional default model

export ARK_API_KEY="your_api_key" # 使用方舟必填 export ARK_MODEL="doubao-seedream-5-0-260128" # 可选：默认模型

Tencent Hunyuan (TokenHub)

腾讯混元（TokenHub）

export HUNYUAN_API_KEY="your_api_key" # Required for Hunyuan export HUNYUAN_MODEL="hy-image-v3.0" # Optional default model

export HUNYUAN_API_KEY="your_api_key" # 使用混元必填 export HUNYUAN_MODEL="hy-image-v3.0" # 可选：默认模型

Zhipu / BigModel

智谱（Zhipu）/ BigModel

export ZHIPUAI_API_KEY="your_api_key" # Required for Zhipu export ZHIPUAI_MODEL="cogview-4" # Optional default model

export ZHIPUAI_API_KEY="your_api_key" # 使用智谱必填 export ZHIPUAI_MODEL="cogview-4" # 可选：默认模型

StepFun / 阶跃星辰

阶跃星辰（StepFun）

export STEP_API_KEY="your_api_key" # Required for StepFun export STEP_MODEL="step-2x-large" # Optional default model

export STEP_API_KEY="your_api_key" # 使用阶跃星辰必填 export STEP_MODEL="step-2x-large" # 可选：默认模型

Google Gemini (international)

Google Gemini（国际版）

export GEMINI_API_KEY="your_api_key" # Required for Gemini export GEMINI_MODEL="gemini-3-pro-image-preview" # Optional default model


Get API Keys:
- DashScope: https://bailian.console.aliyun.com/
- Volcano Ark: https://console.volcengine.com/ark/region:ark+cn-beijing/apikey
- Tencent Hunyuan: https://console.cloud.tencent.com/tokenhub/apikey
- Zhipu: https://bigmodel.cn
- StepFun: https://platform.stepfun.com/interface-key
- Google Gemini: https://aistudio.google.com/

export GEMINI_API_KEY="your_api_key" # 使用Gemini必填 export GEMINI_MODEL="gemini-3-pro-image-preview" # 可选：默认模型


获取API密钥：
- DashScope：https://bailian.console.aliyun.com/
- Volcano Ark：https://console.volcengine.com/ark/region:ark+cn-beijing/apikey
- Tencent Hunyuan：https://console.cloud.tencent.com/tokenhub/apikey
- Zhipu：https://bigmodel.cn
- StepFun：https://platform.stepfun.com/interface-key
- Google Gemini：https://aistudio.google.com/

Config File (Optional)

配置文件（可选）

Create

~/.imagencn.json

for personal defaults, or

.imagencn.json

in a project directory for per-project overrides. API keys stay in environment variables for security.

json

{
  "platform": "ark",
  "model": "doubao-seedream-5-0-260128",
  "size": "2K"
}

All keys are optional. Priority (highest first):

CLI arguments (
```
--platform
```
,
```
--model
```
,
```
--size
```
)
Project config (
```
.imagencn.json
```
in current directory)
User config (
```
~/.imagencn.json
```
)

Environment variables (

DASHSCOPE_MODEL

ARK_MODEL

HUNYUAN_MODEL

ZHIPUAI_MODEL

STEP_MODEL

GEMINI_MODEL

)

Built-in defaults

创建

~/.imagencn.json

设置个人默认值，或在项目目录中创建

.imagencn.json

设置项目级覆盖配置。API密钥需保存在环境变量中以保证安全。

json

{
  "platform": "ark",
  "model": "doubao-seedream-5-0-260128",
  "size": "2K"
}

所有配置项均为可选。优先级（从高到低）：

CLI参数（
```
--platform
```
,
```
--model
```
,
```
--size
```
）
项目配置（当前目录下的
```
.imagencn.json
```
）
用户配置（
```
~/.imagencn.json
```
）

环境变量（

DASHSCOPE_MODEL

ARK_MODEL

HUNYUAN_MODEL

ZHIPUAI_MODEL

STEP_MODEL

GEMINI_MODEL

）

内置默认值

API Endpoints

API端点

Region	Alias	URL
China (default)	`cn`	`https://dashscope.aliyuncs.com/api/v1`
Singapore	`sg`	`https://dashscope-intl.aliyuncs.com/api/v1`
Virginia	`us`	`https://dashscope-us.aliyuncs.com/api/v1`

bash

undefined

区域	别名	URL
国内（默认）	`cn`	`https://dashscope.aliyuncs.com/api/v1`
新加坡	`sg`	`https://dashscope-intl.aliyuncs.com/api/v1`
弗吉尼亚	`us`	`https://dashscope-us.aliyuncs.com/api/v1`

bash

undefined

Switch to Singapore endpoint

切换到新加坡端点

export DASHSCOPE_API_BASE="sg"

Or use full URL

或使用完整URL

export DASHSCOPE_API_BASE="https://dashscope-intl.aliyuncs.com/api/v1"

undefined

export DASHSCOPE_API_BASE="https://dashscope-intl.aliyuncs.com/api/v1"

undefined

Model Selection Guide

模型选择指南

Quick Pick — You Only Need Eight

快速选择 — 只需记住8个模型

What you want	Model	Platform
Default / general (posters, text)	`qwen-image-2.0-pro`	DashScope
Photorealistic (portraits, landscapes)	`wan2.7-image-pro`	DashScope
Edit an image	`qwen-image-edit-max`	DashScope
Cheap & fast	`z-image-turbo`	DashScope
Photo + text combo	`doubao-seedream-5-0-260128`	Volcano Ark
Complex Chinese composition	`hy-image-v3.0`	Tencent Hunyuan
Chinese text in images	`cogview-4`	Zhipu
Ultra-cheap volume gen	`step-image-edit-2`	StepFun
International (non-China)	`gemini-3-pro-image-preview`	Google Gemini

All other models are legacy/snapshot variants.

需求	模型	平台
默认/通用场景（海报、文本）	`qwen-image-2.0-pro`	DashScope
写实风格（人像、风景）	`wan2.7-image-pro`	DashScope
图像编辑	`qwen-image-edit-max`	DashScope
低成本快速生成	`z-image-turbo`	DashScope
照片+文本组合	`doubao-seedream-5-0-260128`	Volcano Ark
复杂中文构图	`hy-image-v3.0`	Tencent Hunyuan
图像中的中文文本	`cogview-4`	Zhipu
超低成本批量生成	`step-image-edit-2`	StepFun
国际场景（非国内）	`gemini-3-pro-image-preview`	Google Gemini

其他模型均为旧版/快照变体。

Full Reference

完整参考

Use Case	Recommended Model
General high-quality (default)	`qwen-image-2.0-pro`
Chinese text/calligraphy	`qwen-image-2.0-pro`
English text on images	`qwen-image-2.0-pro`
Posters with typography	`qwen-image-2.0-pro`
Photorealistic photos (4K)	`wan2.7-image-pro`
Photorealistic photos (2K)	`wan2.7-image`
Portrait photography	`wan2.7-image-pro`
Image editing (best quality)	`qwen-image-edit-max`
Image editing (fast, low-cost)	`qwen-image-edit-plus`
Fast, low-cost generation	`z-image-turbo`
High-fidelity portraits / product shots (fast)	`z-image-turbo`
Fast photorealistic (Wan)	`wan2.2-t2i-flash`
Lower-cost text rendering	`qwen-image-plus`
ByteDance best quality	`doubao-seedream-5-0-260128`
Budget-friendly 4K (ByteDance)	`doubao-seedream-4-0-250828`
Complex Chinese prompts (Tencent)	`hy-image-v3.0`

使用场景	推荐模型
通用高质量生成（默认）	`qwen-image-2.0-pro`
中文文本/书法	`qwen-image-2.0-pro`
图像中的英文文本	`qwen-image-2.0-pro`
带排版的海报	`qwen-image-2.0-pro`
写实风格照片（4K）	`wan2.7-image-pro`
写实风格照片（2K）	`wan2.7-image`
人像摄影	`wan2.7-image-pro`
图像编辑（最佳质量）	`qwen-image-edit-max`
图像编辑（快速低成本）	`qwen-image-edit-plus`
快速低成本生成	`z-image-turbo`
高保真人像/产品拍摄（快速）	`z-image-turbo`
快速写实风格生成（万相）	`wan2.2-t2i-flash`
低成本文本渲染	`qwen-image-plus`
字节跳动最佳质量	`doubao-seedream-5-0-260128`
高性价比4K生成（字节跳动）	`doubao-seedream-4-0-250828`
复杂中文提示词（腾讯）	`hy-image-v3.0`

Platform Quick Comparison

平台快速对比

Feature	DashScope	Ark	Hunyuan	Zhipu	StepFun	Gemini
Best for	Text, variety	Photo+text	Complex CN	CN text in image	Ultra-cheap	International
Max res	4K	4K	2K	2K	1K	2K
SDK	`dashscope`	None	None	None	None	None
Price	Varies	~0.22	~0.20	~0.06	~0.02	~$0.13
Env var	`DASHSCOPE_API_KEY`	`ARK_API_KEY`	`HUNYUAN_API_KEY`	`ZHIPUAI_API_KEY`	`STEP_API_KEY`	`GEMINI_API_KEY`

特性	DashScope	Ark	Hunyuan	Zhipu	StepFun	Gemini
最佳适用场景	文本、多样化风格	照片+文本	复杂中文	图像中的中文文本	超低成本	国际场景
最大分辨率	4K	4K	2K	2K	1K	2K
SDK	`dashscope`	无	无	无	无	无
价格	浮动	~0.22元	~0.20元	~0.06元	~0.02元	~$0.13
环境变量	`DASHSCOPE_API_KEY`	`ARK_API_KEY`	`HUNYUAN_API_KEY`	`ZHIPUAI_API_KEY`	`STEP_API_KEY`	`GEMINI_API_KEY`

Examples

示例

Volcano Ark (ByteDance)

火山方舟（字节跳动）

bash

undefined

bash

undefined

Default Ark model (Seedream 5.0)

默认方舟模型（Seedream 5.0）

ARK_API_KEY="xxx" python scripts/generate_image.py
--platform ark
"A vibrant close-up editorial portrait, Vogue magazine cover style"
portrait.png

ARK_API_KEY="xxx" python scripts/generate_image.py
--platform ark
"充满活力的特写人像，Vogue杂志封面风格"
portrait.png

With 4K output

4K输出

ARK_API_KEY="xxx" python scripts/generate_image.py
--platform ark --model doubao-seedream-4-5-251128 --size 4K
"Breathtaking mountain sunset, golden hour, professional photography"
landscape.png

undefined

ARK_API_KEY="xxx" python scripts/generate_image.py
--platform ark --model doubao-seedream-4-5-251128 --size 4K
"令人惊叹的山脉日落，黄金时段，专业摄影"
landscape.png

undefined

Tencent Hunyuan

腾讯混元

bash

undefined

bash

undefined

Default Hunyuan model (Image 3.0)

默认混元模型（图像3.0）

HUNYUAN_API_KEY="xxx" python scripts/generate_image.py
--platform hunyuan
"An astronaut riding a horse on the moon, cinematic lighting, 8K detail"
scifi.png

HUNYUAN_API_KEY="xxx" python scripts/generate_image.py
--platform hunyuan
"宇航员在月球上骑马，电影级光线，8K细节"
scifi.png

With prompt auto-enhance disabled

禁用提示词自动优化

HUNYUAN_API_KEY="xxx" python scripts/generate_image.py
--platform hunyuan --revise 0
"A cute orange cat napping in sunlight, oil painting style"
cat.png

undefined

HUNYUAN_API_KEY="xxx" python scripts/generate_image.py
--platform hunyuan --revise 0
"一只可爱的橘猫在阳光下打盹，油画风格"
cat.png

undefined

Google Gemini (international)

Google Gemini（国际版）

bash

undefined

bash

undefined

Default Gemini model (Gemini 3 Pro Image)

默认Gemini模型（Gemini 3 Pro Image）

GEMINI_API_KEY="xxx" python scripts/generate_image.py
--platform gemini --size 2K
"A serene Japanese garden with koi pond, soft morning light"
garden.png

undefined

GEMINI_API_KEY="xxx" python scripts/generate_image.py
--platform gemini --size 2K
"宁静的日式花园，带有锦鲤池，柔和的晨光"
garden.png

undefined

Chinese New Year Poster (DashScope)

春节海报（DashScope）

bash

python ~/.claude/skills/imagencn/scripts/generate_image.py \
  "A beautiful Chinese New Year poster with red background, golden text, fireworks and firecrackers" \
  new_year_poster.png

bash

python ~/.claude/skills/imagencn/scripts/generate_image.py \
  "精美的春节海报，红色背景，金色文字，烟花和鞭炮" \
  new_year_poster.png

Photorealistic Landscape (4K)

写实风格风景（4K）

bash

python ~/.claude/skills/imagencn/scripts/generate_image.py \
  --model wan2.7-image-pro \
  --size 4K \
  "Breathtaking sunset over mountain range, golden hour, professional photography" \
  landscape.png

bash

python ~/.claude/skills/imagencn/scripts/generate_image.py \
  --model wan2.7-image-pro \
  --size 4K \
  "令人惊叹的山脉日落，黄金时段，专业摄影" \
  landscape.png

Product Shot

产品拍摄

bash

python ~/.claude/skills/imagencn/scripts/generate_image.py \
  --model wan2.7-image \
  --size 2K \
  "Professional product photography of a coffee cup on marble surface, studio lighting" \
  product.png

bash

python ~/.claude/skills/imagencn/scripts/generate_image.py \
  --model wan2.7-image \
  --size 2K \
  "大理石桌面上的咖啡杯专业产品摄影，影棚光线" \
  product.png