qwen-image-2 — Claude Code skill: what it does, how to install
qwen-image-2 is a Claude Code skill for creating and editing images with Alibaba Qwen-Image-2.0. It responds to Qwen Image and image-generation requests.
no license 240 installs ★ 31 updated 2026-08-31
npx skills add 101-skills/superpowers --skill qwen-image-2 -a claude-codeWhat qwen-image-2 does
qwen-image-2 sends text-to-image and image-editing jobs to Alibaba Qwen-Image-2.0 through the belt CLI. The regular model handles general image creation, while alibaba/qwen-image-2-pro targets layouts where rendered text matters.
Inputs can include reference image URIs, output count, width, height, a negative prompt, watermark settings, prompt expansion, and a seed. A prompt can contain up to 800 characters. Output dimensions must stay between 512×512 and 2048×2048 pixels, and reference-based edits accept one to three images.
The belt CLI from inference.sh is required, followed by belt login. Without an authenticated CLI session, the app cannot run.
What it helps with
- generate an image from a written scene
- edit a composition with several reference images
- render a poster with prominent text
- control output dimensions and image count
- recreate a result with a fixed seed
Example prompts for the agent
- Create a neon-lit city at night with
alibaba/qwen-image-2. - Make a tall sale poster with a red headline and blue subtitle using
alibaba/qwen-image-2-pro; keep prompt expansion off. - Put the clothing from
dress.jpgon the person inperson.jpgwithalibaba/qwen-image-2.
How to install qwen-image-2
1Skills CLI (Vercel)
npx skills add 101-skills/superpowers --skill qwen-image-2 -a claude-code2Manually: put the files in place
~/.claude/skills/qwen-image-2/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/qwen-image-2/
1Skills CLI (Vercel)
npx skills add 101-skills/superpowers --skill qwen-image-2 -a codex2Manually: put the files in place
.agents/skills/qwen-image-2/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add 101-skills/superpowers --skill qwen-image-2 -a cursor2Manually: put the files in place
.cursor/skills/qwen-image-2/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install 101-skills/superpowers tools/image/qwen-image-22Manually: put the files in place
.github/skills/qwen-image-2/SKILL.md1Skills CLI (Vercel)
npx skills add 101-skills/superpowers --skill qwen-image-2 -a gemini-cli2Platform CLI
gemini skills install https://github.com/101-skills/superpowers --path tools/image/qwen-image-2Manually: put the files in place
.devin/skills/qwen-image-2/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add 101-skills/superpowers --skill qwen-image-2 -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about qwen-image-2
How do I install qwen-image-2 in Claude Code?
Run npx skills add 101-skills/superpowers --skill qwen-image-2 -a claude-code, then check ~/.claude/skills/qwen-image-2/SKILL.md.
What does qwen-image-2 do?
It runs Alibaba Qwen-Image-2.0 models through belt for text-based image creation and edits guided by reference images. The Pro variant is intended for designs that contain substantial rendered text.
What is required to run qwen-image-2?
The inference.sh CLI belt is required, along with a completed belt login session.