qwen-image-2-pro
Generate Text-Rich Images with Qwen Pro
Design teams need image prompts that preserve text and layout details. This skill guides Claude, Codex, or Claude Code to call Qwen-Image-2-Pro through inference.sh.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "qwen-image-2-pro" from https://skillstore.io/skills/inference-shell-qwen-image-2-pro.md and its manifest at https://skillstore.io/api/skills/inference-shell-qwen-image-2-pro/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "qwen-image-2-pro". A poster request with the title Grand Opening, a date, and a clean gold background.
Expected outcome:
The skill returns a PNG poster with the requested title, date, dimensions, and style direction.
Using "qwen-image-2-pro". Two reference image URLs and a request to transfer clothing from one image to another.
Expected outcome:
The skill creates two edited image results and keeps the main person from the first reference.
Using "qwen-image-2-pro". A request for four coffee shop logo ideas using a fixed seed.
Expected outcome:
The skill returns four comparable logo variations for review and selection.
Security Audit
SafeAll static matches are documentation false positives, mostly Markdown code fences and inline code spans. The skill transparently calls inference.sh for Qwen image generation and shows no prompt injection, exfiltration, or hidden execution intent.
Risk Factors
⚙️ External commands (39)
🌐 Network access (7)
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/inference-shell-qwen-image-2-pro/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/inference-shell-qwen-image-2-pro?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/inference-shell-qwen-image-2-pro?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/inference-shell-qwen-image-2-pro/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/inference-shell-qwen-image-2-pro.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
inference-shell. (2026). qwen-image-2-pro security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/inference-shell-qwen-image-2-pro/audits/4BibTeX citation
@techreport{inference-shell-inference-shell-qwen-image-2-pro-2026,
author = {inference-shell},
title = {qwen-image-2-pro security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/inference-shell-qwen-image-2-pro/audits/4},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "qwen-image-2-pro security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
- name: "inference-shell"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/inference-shell-qwen-image-2-pro/audits/4"
identifiers:
- type: other
value: "skillstore:inference-shell-qwen-image-2-pro:audit:4"
description: "Skillstore immutable audit report identifier"
Compare variants
2 installable variantsEach author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
inference-shell-qwen-image-2-pro
2026-09-09
inferen-sh-qwen-image-2-pro
2026-09-09
Skillstore Score
Why this score Evidence Confidence: HighWhat You Can Build
Produce Campaign Banners
Create wide promotional graphics with clear sale text, controlled dimensions, and negative prompts for sharper lettering.
Draft Text-Heavy Posters
Generate event posters with title, subtitle, date, and style details in one structured prompt.
Explore Visual Variations
Create several logo or concept options with repeatable seeds before selecting a final direction.
Try These Prompts
Generate one image of a futuristic city at sunset. Use Qwen-Image-2-Pro and keep the default settings.
Create a 1920 by 1080 summer sale banner with the text SUMMER SALE and 50% OFF. Avoid blurry text.
Generate four logo concepts for a coffee shop named Bean and Brew. Use a clean style and a fixed seed.
Use my two reference image URLs. Put the outfit from the second image on the person in the first image.
Best Practices
- State exact text, placement, font style, and color for text-heavy designs.
- Disable prompt extension when exact wording matters more than creative expansion.
- Use seeds, dimensions, and negative prompts to compare results consistently.
Avoid
- Do not send private image URLs unless remote processing is approved.
- Do not rely on the first result without checking text accuracy.
- Do not ask for dense paragraphs when a short headline would work better.
Frequently Asked Questions
Does this skill require inference.sh?
Can it edit existing images?
Does it run Qwen locally?
Which assistants can use it?
Can it render exact text?
How do I make results repeatable?
Developer Details
Author
inference-shellLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
a25199bc7d6b82598536822d1738eb5d5f54025b
Maintenance freshness
7/18/2026
Usage
8 downloads · 193 views
File structure
📄 SKILL.md