imagenCN

ImagenCN - Alibaba Cloud Bailian Text-to-Image Skill

Overview

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

Supports five platforms across nine 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)

Cross-platform support: Windows, macOS, Linux

When to Use This Skill

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
• Any task where AI-generated image with strong Chinese support would be helpful

Workflow

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

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.

Step 2 — Pick a model

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.

Step 3 — Pick a size

Native 2K for Qwen-Image 2.0, 1K/2K/4K for Wan2.7, or an aspect-ratio preset (16:9, 1:1, etc.).

Step 4 — Generate

Run scripts/generate_image.py with the confirmed prompt and output path.

Step 5 — Save

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

Models

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

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

Editing models require an input image via --image (local path or URL). Omit --size to match the input image dimensions.

Qwen-Image legacy (ImageSynthesis API)

Wan Series - Photorealistic Generation (ImageGeneration API)

Z-Image - Lightweight & Fast (MultiModalConversation API)

Volcano Ark - ByteDance Seedream (OpenAI-compatible API)

Tencent Hunyuan (OpenAI-compatible API)

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

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

Usage

Basic Usage

# Default model (qwen-image-2.0-pro, native 2K output)
python ~/.claude/skills/imagenCN/scripts/generate_image.py "A cute cat" output.png

# Photorealistic with Wan model (Wan2.7 supports 4K)
python ~/.claude/skills/imagenCN/scripts/generate_image.py --model wan2.7-image-pro --size 4K "Realistic photo of mountains at sunset" photo.png

# Edit an existing image (requires --image; local path or 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

Size Options

# Use ratio preset
python ~/.claude/skills/imagenCN/scripts/generate_image.py --size 16:9 "Wide landscape" landscape.png

# Use exact dimensions
python ~/.claude/skills/imagenCN/scripts/generate_image.py --size 1280*720 "Custom size" custom.png

Size Presets

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

Advanced Options

# With negative prompt
python ~/.claude/skills/imagenCN/scripts/generate_image.py --negative "blurry, low quality" "High quality portrait" portrait.png

# List all models
python ~/.claude/skills/imagenCN/scripts/generate_image.py --list-models

Requirements

pip install dashscope requests

# Optional: for coloured output and styled tables
pip install rich

Environment Variables

# Alibaba Cloud Bailian (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

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

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

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

# StepFun / 阶跃星辰
export STEP_API_KEY="your_api_key"              # Required for StepFun
export STEP_MODEL="step-2x-large"               # 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

Config File (Optional)

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.

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

All keys are optional. Priority (highest first):

1. CLI arguments (--platform, --model, --size)
2. Project config (.imagenCN.json in current directory)
3. User config (~/.imagenCN.json)
4. Environment variables (DASHSCOPE_MODEL, ARK_MODEL, HUNYUAN_MODEL)
5. Built-in defaults

API Endpoints

# Switch to Singapore endpoint
export DASHSCOPE_API_BASE="sg"

# Or use full URL
export DASHSCOPE_API_BASE="https://dashscope-intl.aliyuncs.com/api/v1"

Model Selection Guide

Quick Pick — You Only Need Eight

All other models are legacy/snapshot variants.

Full Reference

Platform Quick Comparison

Comparison with Imagen (Gemini)

Examples

Volcano Ark (ByteDance)

# Default Ark model (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

# With 4K output
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

Tencent Hunyuan

# Default Hunyuan model (Image 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

# With prompt auto-enhance disabled
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

Chinese New Year Poster (DashScope)

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

Photorealistic Landscape (4K)

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

Product Shot

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