# Image Gen

> Generate images from text prompts via DashScope/Qwen. Use when creating, drawing, or illustrating images.

- Skill: `alibaba/image-gen` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add alibaba/image-gen`
- Raw SKILL.md: https://api.skillmd.com/api/skills/alibaba/image-gen/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: alibaba (https://skillmd.com/u/alibaba)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/alibaba/image-gen

---


# Image Generation

Run `scripts/generate_image.py` relative to this skill's directory.

```bash
python3 SKILL_DIR/scripts/generate_image.py -p "prompt text" -o output.png [-m model] [-s size]
```

Default model: `wanx2.1-t2i-turbo`. Also: `wanx2.1-t2i-plus`, `wanx-v1`. Size default `1024*1024`.

Requires env var `DASHSCOPE_API_KEY` (or `QWEN_API_KEY`).