Skills image-inpainting

📦

image-inpainting

Name: image-inpainting
Author: runcomfy-com

Content revision r1 Safe ⚙️ External commands🌐 Network access📁 Filesystem access

Inpaint Images with RunComfy

Mask-driven image edits can be slow when prompts, masks, and model choices are handled manually. This skill guides Claude, Codex, or Claude Code to run RunComfy inpainting with the right model and inputs.

Supports: Claude Codex Code(CC)

🥉 79 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 "image-inpainting" from https://skillstore.io/skills/runcomfy-com-image-inpainting.md and its manifest at https://skillstore.io/api/skills/runcomfy-com-image-inpainting/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.

Markdown detail GET /skills/runcomfy-com-image-inpainting.md Signed manifest GET /api/skills/runcomfy-com-image-inpainting/manifest Signed lockfile GET /api/skills/runcomfy-com-image-inpainting/lockfile

Test it

Using "image-inpainting". A product photo has a mask over a cluttered background.

Expected outcome:

The skill selects Z-Image Turbo Inpainting, fills the masked background with clean studio paper, and saves the result to the output directory.

Using "image-inpainting". A street photo has masked overhead cables.

Expected outcome:

The skill removes the cables, asks RunComfy to preserve rooflines and sky gradients, and reports where the edited image was downloaded.

Using "image-inpainting". A user describes a local edit but has no mask image.

Expected outcome:

The skill recommends a description-based edit model and frames the prompt to preserve everything outside the requested region.

Security Audit

Safe

v4 • 7/5/2026 Open versioned report

No prompt injection, covert data exfiltration, or malicious filesystem behavior was found in the reviewed skill file. The static findings are false positives from Markdown code formatting, documented RunComfy URLs, sample CLI usage, and normal token storage documentation. The main residual consideration is expected privacy exposure because user-provided image and mask URLs are sent to RunComfy services.

Files scanned

223

Lines analyzed

Review items

False positives ignored

Risk Factors

⚙️ External commands (47)

🌐 Network access (23)

📁 Filesystem access (2)

SKILL.md:206 SKILL.md:206

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 →

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

Copy report link

https://skillstore.io/skills/runcomfy-com-image-inpainting/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/runcomfy-com-image-inpainting/security.svg)](https://skillstore.io/skills/runcomfy-com-image-inpainting?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/runcomfy-com-image-inpainting?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/runcomfy-com-image-inpainting/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/runcomfy-com-image-inpainting.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

runcomfy-com. (2026). image-inpainting security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/runcomfy-com-image-inpainting/audits/4

BibTeX citation

@techreport{runcomfy-com-runcomfy-com-image-inpainting-2026,
  author = {runcomfy-com},
  title = {image-inpainting security audit report (audit version 4)},
  institution = {Skillstore},
  year = {2026},
  number = {4},
  url = {https://skillstore.io/skills/runcomfy-com-image-inpainting/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: "image-inpainting security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
  - name: "runcomfy-com"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/runcomfy-com-image-inpainting/audits/4"
identifiers:
  - type: other
    value: "skillstore:runcomfy-com-image-inpainting:audit:4"
    description: "Skillstore immutable audit report identifier"

Compare variants

3 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

Author / source Skillstore Score Evidence Confidence Skillstore usage Updated

runcomfy-com Recommended Current

runcomfy-com-image-inpainting

Skillstore Score 79

Evidence Confidence High

Skillstore usage 7

Updated

2026-08-21

doany-ai

doany-ai-image-inpainting

Skillstore Score 70

Evidence Confidence High

Skillstore usage 12

Updated

2026-08-21

agentspace-so

agentspace-so-image-inpainting

Skillstore Score 70

Evidence Confidence High

Skillstore usage 9

Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: High

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Clean Product Backgrounds

Replace masked product backgrounds with consistent studio surfaces while preserving the product edges.

Retouch Local Image Defects

Remove small distractions, blemishes, or damaged areas from user-owned images with controlled masks.

Apply Styled Region Replacements

Use LoRA-capable inpainting routes when a masked area must match a brand or visual style.

Try These Prompts

Remove a Masked Object

Inpaint the masked area in [image URL] using [mask URL]. Remove [object] and preserve [areas to keep].

Replace a Background

Replace the masked background in [image URL] with [new background]. Keep the subject unchanged and blend the mask edge naturally.

Tune Cleanup Strength

Use RunComfy inpainting for [image URL] and [mask URL]. Set strength near 0.5 for cleanup and keep nearby textures matched.

Choose the Best Route

Choose the best RunComfy route for this edit. I have [mask or no mask], [image URL], and need [goal], while preserving [constraints].

Best Practices

Use masks that match the source image dimensions and align with the intended edit region.
State what must remain unchanged outside the mask.
Confirm permission before removing watermarks, logos, or identifying marks.

Avoid

Do not reuse a mask from a different source image.
Do not send private or regulated images to external services without approval.
Do not use high strength values for subtle cleanup unless full replacement is intended.

Frequently Asked Questions

Does this skill create masks?

No. It consumes image and mask URLs. Create masks with an image editor or segmentation tool first.

Which model does it use for masked edits?

It defaults to Tongyi MAI Z-Image Turbo Inpainting when a mask is available.

What happens when I do not have a mask?

The skill recommends description-based edit models such as Nano Banana 2 Edit, GPT Image 2 Edit, or FLUX Kontext Pro.

Can it remove watermarks?

It can guide watermark cleanup, but only use it when you own the content or have permission.

Where are results saved?

RunComfy downloads completed results into the output directory selected for the CLI run.

Does it work offline?

No. The RunComfy CLI sends the request to RunComfy model services and downloads the result.

Developer Details

Author

runcomfy-com

License

MIT

Skillstore revision

Version notice

The author did not declare a version.

Repository

https://github.com/runcomfy-com/skills/tree/main/image-inpainting/

Ref

62e2a730c5cd74eab4c7164309d810de660fcea3

Maintenance freshness

7/18/2026

Usage

1 downloads · 0 views

File structure

📄 SKILL.md