imagenty

Use when generating images with Alibaba Cloud Bailian API, especially for Chinese text rendering or photorealistic images

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "imagenty" with this command: npx skills add agents365-ai/imagenty/agents365-ai-imagenty-imagenty

ImagenTY - Alibaba Cloud Bailian Text-to-Image Skill

Overview

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

Supports two model families:

  • Qwen-Image: Excellent at rendering complex Chinese/English text
  • Wan Series: Photorealistic images and photography-grade visuals

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 explicitly requests Alibaba Cloud / Bailian / Qwen / Wan models
  • Any task where AI-generated image with strong Chinese support would be helpful

Models

Qwen-Image - Text Rendering Specialist

ModelDescription
qwen-image-plusDefault. Best for Chinese/English text, posters, illustrations

Wan Series - Photorealistic Generation

ModelDescription
wan2.6-t2iRecommended. Latest version, flexible sizing
wan2.5-t2i-previewHigh quality, up to 768x2700
wan2.2-t2i-flashSpeed-optimized
wan2.2-t2i-plusProfessional tier
wanx2.1-t2i-turboFast execution
wanx2.1-t2i-plusProfessional tier
wanx2.0-t2i-turboEarlier generation

Usage

Basic Usage

# Default model (qwen-image-plus)
python ~/.claude/skills/imagenty/scripts/generate_image.py "A cute cat" output.png

# Photorealistic with Wan model
python ~/.claude/skills/imagenty/scripts/generate_image.py --model wan2.6-t2i "Realistic photo of mountains at sunset" photo.png

Size Options

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

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

Size Presets

Qwen-Image:

  • 16:9 -> 1664x928
  • 9:16 -> 928x1664
  • 1:1 -> 1024x1024
  • 4:3 -> 1216x912
  • 3:4 -> 912x1216

Wan Series:

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

Advanced Options

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

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

Requirements

pip install dashscope requests

Environment Variables

# Required - Alibaba Cloud Bailian API Key
export DASHSCOPE_API_KEY="your_api_key"

# Optional - Set default model
export DASHSCOPE_MODEL="wan2.6-t2i"

# Optional - Set API endpoint (default: China)
export DASHSCOPE_API_BASE="cn"  # or full URL

Get API Key: https://bailian.console.aliyun.com/

API Endpoints

RegionAliasURL
China (default)cnhttps://dashscope.aliyuncs.com/api/v1
Singaporesghttps://dashscope-intl.aliyuncs.com/api/v1
Virginiaushttps://dashscope-us.aliyuncs.com/api/v1
# 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

Use CaseRecommended Model
Chinese text/calligraphyqwen-image-plus
English text on imagesqwen-image-plus
Posters with typographyqwen-image-plus
Photorealistic photoswan2.6-t2i
Portrait photographywan2.6-t2i
Fast generationwan2.2-t2i-flash
High quality artwan2.5-t2i-preview

Comparison with Imagen (Gemini)

FeatureImagenTY (Bailian)Imagen (Gemini)
Chinese text renderingExcellentGood
English text renderingExcellentGood
Photorealistic imagesExcellentGood
SpeedMediumFast
Model variety8 models3 models
Max resolution1440x14402K

Examples

Chinese New Year Poster

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

Photorealistic Landscape

python ~/.claude/skills/imagenty/scripts/generate_image.py \
  --model wan2.6-t2i \
  --size 16:9 \
  "Breathtaking sunset over mountain range, golden hour, professional photography" \
  landscape.png

Product Shot

python ~/.claude/skills/imagenty/scripts/generate_image.py \
  --model wan2.6-t2i \
  "Professional product photography of a coffee cup on marble surface, studio lighting" \
  product.png

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

video-podcast-maker

No summary provided by upstream source.

Repository SourceNeeds Review
Automation

drawio

No summary provided by upstream source.

Repository SourceNeeds Review
Automation

clinic-visit-prep

帮助患者整理就诊前问题、既往记录、检查清单与时间线,不提供诊断。;use for healthcare, intake, prep workflows;do not use for 给诊断结论, 替代医生意见.

Archived SourceRecently Updated