ImagenCN — AI Image Generation with Chinese Text Excellence

中文文档

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

A Claude Code / OpenClaw skill for AI image generation using Alibaba Cloud Bailian, ByteDance Volcano Ark, Tencent Hunyuan, Zhipu BigModel, StepFun, and Google Gemini APIs.

📋 Model Reference — browse all 31 models with pricing, resolution, and feature comparison.

Pipeline

Features

• Alibaba Cloud Bailian (DashScope): Qwen-Image 2.0, Edit, Wan Series, Z-Image — 21 models
• ByteDance Volcano Ark: Doubao-Seedream series (5.0/4.5/4.0) — 3 models, up to 4K
• Tencent Hunyuan: Hunyuan Image 3.0 — flagship, complex Chinese composition
• Zhipu / BigModel: CogView-4, GLM-Image — 3 models, native Chinese text in images
• StepFun / 阶跃星辰: Step-2X, Step-Image-Edit-2 — 2 models, ultra-cheap volume gen
• Google Gemini (international): Gemini 3 Pro Image — 1 model, 512/1K/2K plus aspect ratios
• Multiple size presets: 1:1, 16:9, 9:16, 4:3, 3:4, plus 1K/2K/3K/4K
• Cross-platform: Windows, macOS, Linux support
• Multiple API regions: China (default), Singapore, Virginia (DashScope)

Installation

Claude Code Marketplace (recommended)

/plugin install imagenCN@365-skills

Or tell your coding agent:

help me to install https://github.com/Agents365-ai/imagenCN.git

Manual

# Global install
git clone https://github.com/Agents365-ai/imagenCN.git ~/.claude/skills/imagenCN

# Project-specific
git clone https://github.com/Agents365-ai/imagenCN.git .claude/skills/imagenCN

OpenClaw

git clone https://github.com/Agents365-ai/imagenCN.git skills/imagenCN

SkillsMP

Search imagenCN on skillsmp.com for one-click install.

Requirements

System Requirements

• Python 3.8+
• pip

Install Dependencies

pip install dashscope requests

API Keys

# Alibaba Cloud Bailian (DashScope)
export DASHSCOPE_API_KEY="your_api_key"
# Get key: https://bailian.console.aliyun.com/

# ByteDance Volcano Ark (optional)
export ARK_API_KEY="your_api_key"
# Get key: https://console.volcengine.com/ark/region:ark+cn-beijing/apikey

# Tencent Hunyuan (optional)
export HUNYUAN_API_KEY="your_api_key"
# Get key: https://console.cloud.tencent.com/tokenhub/apikey

# Zhipu / BigModel (optional)
export ZHIPUAI_API_KEY="your_api_key"
# Get key: https://bigmodel.cn

# StepFun / 阶跃星辰 (optional)
export STEP_API_KEY="your_api_key"
# Get key: https://platform.stepfun.com/interface-key

# Google Gemini (optional, international)
export GEMINI_API_KEY="your_api_key"
# Get key: https://aistudio.google.com/

Config File (Optional)

Create ~/.imagenCN.json for personal defaults:

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

Project-level .imagenCN.json overrides user-level. CLI args override both.

Optional Environment Variables

# Set default model per platform
export DASHSCOPE_MODEL="wan2.7-image-pro"       # DashScope default
export ARK_MODEL="doubao-seedream-5-0-260128"   # Volcano Ark default
export HUNYUAN_MODEL="hy-image-v3.0"            # Tencent Hunyuan default
export ZHIPUAI_MODEL="cogview-4"                # Zhipu default
export STEP_MODEL="step-2x-large"               # StepFun default
export GEMINI_MODEL="gemini-3-pro-image-preview" # Google Gemini default

# Set API endpoint (DashScope only, default: cn)
export DASHSCOPE_API_BASE="cn"  # or "sg", "us", or full URL

Quick Start

Natural Language (Claude Code)

Just tell Claude what you want:

Generate an image of a cute orange cat
Create a poster with text "Happy New Year" in Chinese
Make a photorealistic 4K mountain sunset photo using wan2.7-image-pro
Generate a 16:9 landscape wallpaper

Command Line

# Basic usage (default model: qwen-image-2.0-pro, native 2K)
python scripts/generate_image.py "A cute cat" output.png

# Photorealistic 4K with Wan2.7 (DashScope)
python scripts/generate_image.py --model wan2.7-image-pro --size 4K "Mountain sunset" photo.png

# Volcano Ark (ByteDance) — requires ARK_API_KEY
python scripts/generate_image.py --platform ark "Editorial portrait, Vogue style" portrait.png

# Tencent Hunyuan — requires HUNYUAN_API_KEY
python scripts/generate_image.py --platform hunyuan "Astronaut on the moon, cinematic" scifi.png

# Google Gemini (international) — requires GEMINI_API_KEY
python scripts/generate_image.py --platform gemini "Japanese garden, morning light" garden.png

# Edit an existing image (DashScope, requires --image)
python scripts/generate_image.py --model qwen-image-edit-max --image input.png "Change the background to a beach" edited.png

# With negative prompt (DashScope)
python scripts/generate_image.py --negative "blurry" "High quality portrait" portrait.png

# List all 6 platforms' models
python scripts/generate_image.py --list-models

Models

Size Presets

Qwen-Image 2.0 (native 2K):

• 1:1 → 2048×2048 (default)
• 16:9 → 2688×1536
• 9:16 → 1536×2688
• 4:3 → 2304×1728
• 3:4 → 1728×2304
• 1K → 1024×1024
• 2K → 2048×2048

Qwen-Image legacy:

• 1:1 → 1328×1328
• 16:9 → 1664×928
• 9:16 → 928×1664
• 4:3 → 1472×1104
• 3:4 → 1104×1472

Z-Image (pixel area 512×512 to 2048×2048):

• 1:1 → 1024×1024 (default)
• 16:9 → 1280×720
• 9:16 → 720×1280
• 2:3 → 1024×1536
• 3:2 → 1536×1024

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

• 1:1 → 1024×1024
• 1:1-large → 1280×1280
• 16:9 → 1280×720
• 9:16 → 720×1280
• 4:3 → 1200×900
• 3:4 → 900×1200
• 2:1 → 1440×720

Volcano Ark (Seedream):

• 1:1 → 2048×2048
• 16:9 → 2848×1600
• 9:16 → 1600×2848
• 4:3 → 2304×1728
• 3:4 → 1728×2304
• 1K / 2K / 3K / 4K (model-dependent)

Tencent Hunyuan (colon-separated):

• 1:1 → 1024:1024
• 16:9 → 1920:1080
• 9:16 → 1080:1920
• 4:3 → 1600:1200
• 3:4 → 1200:1600
• 3:2 → 1920:1280
• 2:3 → 1280:1920

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)

API Endpoints

Support

If this project helps you, consider supporting the author:

Author

Agents365-ai

• Bilibili: https://space.bilibili.com/441831884
• GitHub: https://github.com/Agents365-ai

License

CC BY-NC 4.0 — free for non-commercial use. Commercial use requires permission.