Index of every page on this site: llms.txt
All skills
inference-sh avatar

/qwen-image-2-pro

@c895a47
by inference.shinference-sh/skills819 stars
108
Run it yourself

Generate images with Alibaba Qwen-Image-2.0-Pro via inference.sh CLI. Professional text rendering, fine-grained realism, enhanced semantic adherence. Ideal for posters, banners, and text-heavy designs. Triggers: qwen image pro, qwen-image-pro, qwen 2 pro, alibaba image pro, dashscope pro, professional text rendering

Use this Skill: https://skilld.dev/gh/inference-sh/skills/qwen-image-2-pro

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈84 tokens for metadata: the name and description. ≈1.5k when used: this file.

Description uses 4.2% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈336 characters, or 4.2%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Install the belt CLI skill: npx skills add belt-sh/cli

Qwen-Image Pro - Professional Image Generation

Generate images with Alibaba Qwen-Image-2.0-Pro via inference.sh CLI. Best for professional text rendering and complex designs.

Qwen-Image-2.0-Pro

Quick Start

Requires inference.sh CLI (belt). Install instructions

belt login

belt app run alibaba/qwen-image-2-pro --input '{"prompt": "Poster with title \"Welcome!\" in bold blue text"}'

Pro Model Capabilities

  • Professional Text Rendering: Multi-line and paragraph-level text with fine-grained detail
  • Fine-grained Realism: Better textures and photorealistic scenes
  • Stronger Semantic Adherence: More accurately follows complex prompts
  • Complex Designs: Ideal for text + image combinations

Examples

Basic Text-to-Image

belt app run alibaba/qwen-image-2-pro --input '{
  "prompt": "A futuristic cityscape at sunset with flying cars"
}'

Text-Heavy Poster

belt app run alibaba/qwen-image-2-pro --input '{
  "prompt": "Healing-style hand-drawn poster featuring three puppies playing with a ball. The main title \"Come Play Ball!\" is prominently displayed at the top in bold, blue cartoon font. Below, the subtitle \"Join the Fun!\" appears in green font.",
  "width": 1024,
  "height": 1536,
  "prompt_extend": false
}'

Marketing Banner

belt app run alibaba/qwen-image-2-pro --input '{
  "prompt": "Professional marketing banner for summer sale. Large text \"SUMMER SALE\" in white on gradient sunset background. \"50% OFF\" in yellow below. Clean, modern design.",
  "width": 1920,
  "height": 1080,
  "prompt_extend": false,
  "negative_prompt": "blurry text, distorted text, low quality"
}'

Multiple Variations

belt app run alibaba/qwen-image-2-pro --input '{
  "prompt": "Minimalist logo design for a coffee shop called \"Bean & Brew\"",
  "num_images": 4
}'

Image Editing (Style Transfer)

belt app run alibaba/qwen-image-2-pro --input '{
  "prompt": "Make the person from Image 1 wear the outfit from Image 2",
  "reference_images": [
    "https://example.com/person.jpg",
    "https://example.com/outfit.jpg"
  ],
  "num_images": 2
}'

Reproducible Generation

belt app run alibaba/qwen-image-2-pro --input '{
  "prompt": "Abstract geometric art in blue and gold",
  "seed": 12345
}'

Input Options

Parameter Type Description
prompt string Required. What to generate or edit (max 800 chars)
reference_images array Input images for editing (1-3 images)
num_images integer Number of images to generate (1-6)
width integer Output width in pixels (512-2048)
height integer Output height in pixels (512-2048)
watermark boolean Add "Qwen-Image" watermark
negative_prompt string Content to avoid (max 500 chars)
prompt_extend boolean Enable prompt rewriting (default: true)
seed integer Random seed for reproducibility (0-2147483647)

Size constraint: Total pixels must be between 512×512 and 2048×2048.

Output

Field Type Description
images array The generated or edited images (PNG format)
output_meta object Metadata with dimensions and count

Text Rendering Tips

For best text results with the Pro model:

  1. Use quotes around exact text: "Title: \"Hello World!\""
  2. Specify font details: color, style, size, position
  3. Disable prompt_extend: Set prompt_extend: false for precise control
  4. Use negative prompts: "blurry text, distorted text, low quality"

Example prompt structure:

Poster with the title "GRAND OPENING" in large red serif font at the top center.
Below, the date "March 15, 2024" in smaller black text.
Background: elegant gold and white gradient.
Style: professional, clean, modern.

Recommended Negative Prompt

{
  "negative_prompt": "low resolution, low quality, deformed limbs, deformed fingers, oversaturated, waxy, no facial details, overly smooth, AI-like, chaotic composition, blurry text, distorted text"
}

Sample Workflow

# 1. Generate sample input to see all options
belt app sample alibaba/qwen-image-2-pro --save input.json

# 2. Edit the prompt
# 3. Run
belt app run alibaba/qwen-image-2-pro --input input.json

Python SDK

from inferencesh import inference

client = inference()

# Text-heavy poster
result = client.run({
    "app": "alibaba/qwen-image-2-pro",
    "input": {
        "prompt": "Poster with title \"Welcome!\" in bold blue text at top",
        "width": 1024,
        "height": 1536,
        "prompt_extend": False
    }
})
print(result["output"])

# Stream live updates
for update in client.run({
    "app": "alibaba/qwen-image-2-pro",
    "input": {
        "prompt": "Professional product photography of a watch"
    }
}, stream=True):
    if update.get("progress"):
        print(f"progress: {update['progress']}%")
    if update.get("output"):
        print(f"output: {update['output']}")

Related Skills

# Standard Qwen-Image (faster, general use)
npx skills add inference-sh/skills@qwen-image

# Full platform skill (all apps)
npx skills add inference-sh/skills@infsh-cli

# All image generation models
npx skills add inference-sh/skills@ai-image-generation

Browse all image apps: belt app list --category image

Documentation

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 alert3d5 checks · Risk SAFE
  • Gen Agent Trust Hub3d

    This skill provides instructions and examples for using the Alibaba Qwen-Image-2.0-Pro image generation model through the inference-sh CLI and SDK. No security issues were detected.

  • Socket3d

    No alerts

  • Snyk3d

    Risk: CRITICAL · 1 issue

  • Runlayer8mo

    1/1 file flagged

  • ZeroLeaks7mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at c895a47. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 days ago.

Activeupdated 4 days ago
What it can do
Runs commands
All 1 allowed tools
Bash(belt *)
  • CLI
  • qwen
  • alibaba
  • image-generation
  • text-rendering
  • dashscope
  • inference-sh
  • poster-design
  • banner-generation

README badge

README badge for inference-sh/skills/qwen-image-2-pro

Generates images using Alibaba's Qwen-Image-2.0-Pro model via the inference.sh CLI, with a focus on professional text rendering and complex semantic control. Best for posters, banners, and designs that require legible, multi-line text or style transfer via reference images.

Generated from the current SKILL.md.

What's the difference between Qwen-Image-2-Pro and the standard Qwen-Image model?
The Pro model offers professional text rendering, fine-grained realism, and stronger semantic adherence to complex prompts. The standard model is faster and better for general use cases.
Does this skill support image editing or style transfer?
Yes. You can pass 1-3 reference images via the `reference_images` parameter to perform edits like outfit swapping or style transfer.
What image dimensions are supported?
Width and height can each range from 512 to 2048 pixels, with a total pixel count between 512×512 and 2048×2048.
How do I get the best text rendering results?
Use quotes around exact text, specify font details (color, style, position), set `prompt_extend: false` for precise control, and include a negative prompt like 'blurry text, distorted text'.
Do I need to install anything before using this skill?
Yes. You must first install the belt CLI skill with `npx skills add belt-sh/cli`, then run `belt login` to authenticate with inference.sh.

Generated from the current SKILL.md. These answers refresh after source changes.