Skip to main content
skill CX Codex

qwen-image-2-pro — Claude Code skill: image generation with text

qwen-image-2-pro — a skill for Claude Code and Cursor that generates images via Alibaba Qwen-Image-2.0-Pro. Renders multi-line text in posters and banners.

no license 239 installs ★ 31 updated 2026-08-31

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add 101-skills/superpowers --skill qwen-image-2-pro -a claude-code
Open on GitHub

What qwen-image-2-pro does

Calls the Qwen-Image-2.0-Pro model through the belt CLI from inference.sh. The Pro model handles text better than the base version: multi-line titles, long captions, complex text-and-image layouts. Pass exact label text in quotes with color, font and position; set resolution from 512×512 to 2048×2048, number of variants (up to six), negative prompt and seed for reproducibility.

For precise text rendering, turn off prompt_extend (on by default) and add blurry text, distorted text, low quality to the negative prompt. The model can edit images using references — up to three input images, with the prompt describing the edit. Without the belt CLI installed, the skill won't run: npx skills add belt-sh/cli.

What it helps with

  • create a poster with headline and subheadline in specified colors
  • build a marketing banner with large text on a gradient
  • draw a logo with a label in a chosen style
  • transfer clothing from one photo onto a person in another
  • get several image variants from a single prompt

Example prompts for the agent

  • Draw a 1024×1536 poster: title "Welcome!" in bold blue at the top, subtitle "Start Now" in green below
  • Make a 1920×1080 banner for a summer sale: "SUMMER SALE" in white on a sunset gradient, "50% OFF" in yellow underneath
  • Create four logo variants for a coffee shop called "Bean & Brew", minimalist style

How to install qwen-image-2-pro

1Skills CLI (Vercel)

npx skills add 101-skills/superpowers --skill qwen-image-2-pro -a claude-code

2Manually: put the files in place

~/.claude/skills/qwen-image-2-pro/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/qwen-image-2-pro/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about qwen-image-2-pro

How do I install qwen-image-2-pro in Claude Code?

First install the belt CLI: npx skills add belt-sh/cli. Then add the skill: npx skills add 101-skills/superpowers --skill qwen-image-2-pro -a claude-code. The skill file will be at ~/.claude/skills/qwen-image-2-pro/SKILL.md.

What does qwen-image-2-pro do?

It generates images via the Alibaba Qwen-Image-2.0-Pro model. The main difference from the base model is high-quality multi-line text rendering in posters, banners and marketing materials.

How does qwen-image-2-pro differ from regular qwen-image?

The Pro version renders text better: multi-line headings, long captions, accurate adherence to complex prompts. The base model is faster and suited to images without text or with a single short word.

Similar skills

All skills for AI and ML →

From the same set81

The whole set →
pitch-deck-visuals pitch-deck-visuals builds an investor-deck outline with slide design rules and data visuals. Use it for fundraising decks, demo days, grant proposals, or startup presentations. CX Codex +1 240installs ai-rag-pipeline ai-rag-pipeline — a skill for building RAG pipelines: web search supplies the facts, a model writes the cited answer. Handy for research agents and claim checking. CX Codex +1 240installs nano-banana-2 Generates images with Google Gemini 3.1 Flash Image Preview (Nano Banana 2) through the belt CLI. Runs on text prompts, edits existing images, and accepts up to 14 input files. CX Codex +1 240installs qwen-image-2 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. CX Codex +1 240installs linkedin-content linkedin-content — a skill for drafting LinkedIn posts: hook formulas, formatting rules, post types, character limits and the signals the feed rewards. CX Codex +1 239installs widgets-ui widgets-ui — a skill for Claude Code, Cursor, Codex and other agents: builds React/Next.js components from JSON descriptions. The agent outputs a widget structure; the renderer assembles forms, cards and layouts in the project. CX Codex +1 239installs javascript-sdk javascript-sdk teaches the agent to wire the inference.sh JavaScript/TypeScript client into your app: running AI apps, streaming progress and building agents in code. CX Codex +1 239installs llm-models llm-models queries over a hundred LLMs through OpenRouter using the belt command-line tool directly from your agent. Selects cost-effective models automatically. CX Codex +1 238installs

Project sponsors

Companies that keep this analytics open