Skills qwen-image-2-pro
๐Ÿ“ฆ

qwen-image-2-pro

Content revision r2 Safe โš™๏ธ External commands๐ŸŒ Network access

Generate Professional Images with Qwen Image Pro

Text-heavy image prompts often produce weak layouts and unreadable lettering. This skill guides Qwen-Image-2.0-Pro generation and editing through inference.sh.

Supports: Claude Codex Code(CC)
๐Ÿฅ‰ 78 Bronze

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "qwen-image-2-pro" from https://skillstore.io/skills/inferen-sh-qwen-image-2-pro.md and its manifest at https://skillstore.io/api/skills/inferen-sh-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 vertical grand-opening poster with a red serif title, event date, and elegant gold background.

Expected outcome:

A generated PNG poster with the requested title hierarchy, event date, vertical layout, and gold visual treatment.

Using "qwen-image-2-pro". Four minimalist logo concepts for a coffee shop named Bean and Brew.

Expected outcome:

  • Four generated PNG concepts with distinct compositions.
  • Output metadata describing image dimensions and count.

Using "qwen-image-2-pro". Edit a portrait so the person wears clothing shown in a second reference image.

Expected outcome:

Two edited PNG variations that preserve the person while applying the referenced outfit.

Security Audit

Safe
v5 โ€ข 8/6/2026 Open versioned report

All 49 static matches are false positives caused by Markdown code formatting, documented CLI examples, public links, and parameter names. The skill openly uses belt and inference.sh for cloud image generation; no hidden execution, unsafe interpolation, reconnaissance, or prompt injection was found.

1
Files scanned
209
Lines analyzed
0
Review items
0
False positives ignored
No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.
Audited by: codex View Audit History โ†’
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.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/inferen-sh-qwen-image-2-pro/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/inferen-sh-qwen-image-2-pro/security.svg)](https://skillstore.io/skills/inferen-sh-qwen-image-2-pro?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/inferen-sh-qwen-image-2-pro?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/inferen-sh-qwen-image-2-pro/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/inferen-sh-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 ยท BibTeX ยท CFF)

APA citation

inferen-sh. (2026). qwen-image-2-pro security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/inferen-sh-qwen-image-2-pro/audits/5

BibTeX citation

@techreport{inferen-sh-inferen-sh-qwen-image-2-pro-2026, author = {inferen-sh}, title = {qwen-image-2-pro security audit report (audit version 5)}, institution = {Skillstore}, year = {2026}, number = {5}, url = {https://skillstore.io/skills/inferen-sh-qwen-image-2-pro/audits/5}, 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 5)" version: "unspecified" type: report authors: - name: "inferen-sh" date-released: "2026-08-06" url: "https://skillstore.io/skills/inferen-sh-qwen-image-2-pro/audits/5" identifiers: - type: other value: "skillstore:inferen-sh-qwen-image-2-pro:audit:5" description: "Skillstore immutable audit report identifier"

Compare variants

2 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Highest Skillstore Score
inference-shell Recommended

inference-shell-qwen-image-2-pro

Skillstore Score 79
Evidence Confidence High
Skillstore usage 16
Updated

2026-08-21

inferen-sh Current

inferen-sh-qwen-image-2-pro

Skillstore Score 78
Evidence Confidence High
Skillstore usage 12
Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: High
55
Architecture
85
Maintainability
87
Content
70
Community
83
Spec Compliance

What You Can Build

Create Campaign Posters

Generate posters and banners with specified titles, typography, colors, and layouts.

Produce Visual Variations

Create several concepts from one brief for fast comparison and review.

Edit Reference Images

Combine visual references for outfit changes, style transfer, and guided image edits.

Try These Prompts

Generate a Simple Image
Create an image of [subject] in [style], with [lighting] and a [color palette] palette.
Design a Text Poster
Create a [format] poster titled "[exact title]" in [font style]. Place [subtitle] at [position] over [background].
Generate Multiple Concepts
Create [number] distinct variations for [brand or product]. Keep [required elements] consistent while varying composition, lighting, and visual style.
Direct a Reference Edit
Using [reference image descriptions], change [target element] to [desired result]. Preserve [identity or structure] and avoid [unwanted changes].

Best Practices

  • Place exact visible text in quotation marks and describe its font, color, size, and position.
  • Disable prompt extension when precise wording or layout must remain unchanged.
  • Use negative prompts and fixed seeds when comparing controlled variations.

Avoid

  • Do not submit confidential images or text without approval for external cloud processing.
  • Do not request dimensions outside the documented pixel limits.
  • Do not assume generated text or visual details are accurate without review.

Frequently Asked Questions

What does this skill generate?
It generates and edits PNG images with Alibaba Qwen-Image-2.0-Pro through inference.sh.
Does it require an account?
Yes. The belt CLI requires inference.sh authentication and access to the model.
Can it render text inside images?
Yes. It targets text-heavy designs, but every result should be checked for spelling and layout errors.
Can it edit existing images?
Yes. A request can include one to three reference image URLs for guided editing.
Can results be reproduced?
A fixed seed improves reproducibility, although service or model changes may affect later results.
Where are prompts and images processed?
They are sent through inference.sh to an external cloud model, so review data policies before using sensitive material.

Developer Details

Author

inferen-sh

License

MIT

Skillstore revision

r2

Version notice

The author did not declare a version.

Ref

4121de961d1b6f2ffca856260e239505c302452c

Maintenance freshness

8/7/2026

Usage

10 downloads ยท 178 views

File structure

๐Ÿ“„ SKILL.md