# imagencn

Generates images through DashScope, Ark, Hunyuan, FLUX, and OpenAI APIs. Useful when you need photorealistic renders, artwork, or Chinese typography in coding agents.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 1700 installs · ★ 92
- Author: Agents365-ai
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/Agents365-ai/365-skills/tree/HEAD/plugins/imagencn/skills/imagencn/SKILL.md
- Updated: 2026-10-16
- HTML: https://affpapa.org/en/nevibecode/skills/imagencn

## What it does

The skill connects coding agents to nine image generation platforms via a Python script. It handles providers such as Alibaba Cloud Bailian, ByteDance Volcano Ark, and Tencent Hunyuan, alongside international APIs from Google, xAI, OpenAI, and Black Forest Labs. Before sending any API call, the workflow presents three refined prompt directions covering lighting, composition, and mood. The default model is `qwen-image-2.0-pro`. It defaults to the China region endpoint.

Running generation requires `python3` on your machine and a configured `DASHSCOPE_API_KEY` environment variable. Without this key, requests sent to default models will fail. For editing tasks, Qwen-Image Edit models require an existing file provided through the `--image` flag. You can also inspect details and pricing for all 44 supported models by opening the local `models.html` document in your browser.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add Agents365-ai/365-skills --skill imagencn -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/imagencn/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/imagencn/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add Agents365-ai/365-skills --skill imagencn -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/imagencn/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add Agents365-ai/365-skills --skill imagencn -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/imagencn/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install Agents365-ai/365-skills imagencn
```

2. **Manually: put the files in place**
- File: `.github/skills/imagencn/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add Agents365-ai/365-skills --skill imagencn -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/Agents365-ai/365-skills --path plugins/imagencn/skills/imagencn
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/imagencn/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add Agents365-ai/365-skills --skill imagencn -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/Agents365-ai/365-skills/tree/HEAD/plugins/imagencn/skills/imagencn/SKILL.md

## When to use it
- render images with legible Chinese calligraphy or typography
- refine vague image prompts into detailed visual options
- modify existing pictures using Qwen-Image Edit models
- generate visuals using FLUX, OpenAI, or DashScope endpoints

## Example prompts
- Generate a photorealistic poster with Chinese text using qwen-image-2.0-pro
- Edit input.png using qwen-image-edit-max to change the background
- Open models.html in my browser to compare model resolutions

## Similar
- [baoyu-image-gen](https://affpapa.org/en/nevibecode/skills/baoyu-image-gen.md) — skill · 33600 installs
- [canghe-image-gen](https://affpapa.org/en/nevibecode/skills/canghe-image-gen.md) — skill · 594 installs
- [qianwen-model-selector](https://affpapa.org/en/nevibecode/skills/qianwen-model-selector.md) — skill · 5500 installs
- [flux-2-klein](https://affpapa.org/en/nevibecode/skills/flux-2-klein.md) — skill · 436000 installs
- [image](https://affpapa.org/en/nevibecode/skills/image.md) — skill · 87300 installs
- [videoagent-image-studio](https://affpapa.org/en/nevibecode/skills/videoagent-image-studio.md) — skill · 5600 installs

From the same set: [agents365-ai/365-skills](https://affpapa.org/en/nevibecode/by/agents365-ai/365-skills.md) — 21 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md