Image Edit
Route image-edit requests to the right RunComfy model and CLI invocation without trial-and-error across Nano Banana, GPT Image 2, Flux Kontext, and Z-Image Turbo.
Overview
Image Edit is an agent skill for the Build phase that routes image-edit intent to the correct RunComfy model and CLI call with model-specific prompting guidance.
Install
npx skills add https://github.com/agentspace-so/runcomfy-skills --skill image-editWhat is this skill?
- Smart intent router across 4 documented edit models (batch identity edit, multilingual text rewrite, single-ref fidelity
- Bundles model-specific prompting patterns to reduce wasted iterations
- Nano Banana Edit supports batch edits up to 20 images with identity-preserving default
- OpenAI GPT Image 2 Edit for multi-ref composition and in-image headline rewrite
- Triggers on image edit, i2i, swap background, remove object, and explicit single or batch edit asks
- Routes among 4 named edit models in the RunComfy catalog
- Nano Banana Edit batch up to 20 images
- Invokes `runcomfy run <vendor>/<model>/edit` via local CLI
Adoption & trust: 30 installs on skills.sh; 2 GitHub stars; 1/3 security scanners passed (skills.sh audits).
What problem does it solve?
You know you need an image edit but the RunComfy catalog offers several edit models with different strengths, so ad-hoc picks waste runs and iterations.
Who is it for?
Solo builders generating or refining visuals via RunComfy CLI who want batch edits, inpainting, or in-image text changes without manually studying each vendor model page.
Skip if: Pure text-to-image generation from scratch with no source image, or teams not using RunComfy and its local CLI.
When should I use this skill?
User asks for image edit, edit image, image-to-image, i2i, swap background, remove object, rewrite headline, or explicit single or batch image edits.
What do I get? / Deliverables
Your agent selects Nano Banana, GPT Image 2, Flux Kontext, or Z-Image Turbo Inpaint with aligned prompts and runs `runcomfy run` for sharper edits on the first model choice.
- Chosen model slug and edit invocation
- Model-aligned edit prompt
- Executed or scripted `runcomfy run` edit job
Recommended Skills
Journey fit
Image editing is wired into the product or content pipeline during build when you connect generative media tools to your app or asset workflow. The skill is an integration router over `runcomfy run <vendor>/<model>/edit`, not a design brief or launch playbook.
How it compares
Use this RunComfy skill router instead of guessing model slugs in generic chat image requests.
Common Questions / FAQ
Who is image-edit for?
Indie builders and content-focused developers who already use RunComfy and want an agent to pick the right edit model and prompt pattern for i2i tasks.
When should I use image-edit?
During build when integrating generative assets—when you say image edit, i2i, swap background, remove object, rewrite headline, or ask to edit one or many images through RunComfy.
Is image-edit safe to install?
Review the Security Audits panel on this Prism page and treat RunComfy CLI credentials and uploaded images as sensitive before enabling network and shell access for your agent.
SKILL.md
READMESKILL.md - Image Edit
# Image Edit — Pro Pack on RunComfy [runcomfy.com](https://www.runcomfy.com/?utm_source=skills.sh&utm_medium=skill&utm_campaign=image-edit) · [Nano Banana Edit](https://www.runcomfy.com/models/google/nano-banana-2/edit?utm_source=skills.sh&utm_medium=skill&utm_campaign=image-edit) · [GPT Image 2 Edit](https://www.runcomfy.com/models/openai/gpt-image-2/edit?utm_source=skills.sh&utm_medium=skill&utm_campaign=image-edit) · [Flux Kontext](https://www.runcomfy.com/models/blackforestlabs/flux-1-kontext-pro/image-to-image?utm_source=skills.sh&utm_medium=skill&utm_campaign=image-edit) · [Z-Image Inpaint](https://www.runcomfy.com/models/tongyi-mai/z-image/turbo/inpainting?utm_source=skills.sh&utm_medium=skill&utm_campaign=image-edit) · [GitHub](https://github.com/agentspace-so/runcomfy-skills/tree/main/image-edit) **Image edit, intent-routed.** This skill doesn't lock you to one model — it picks the right edit model in the RunComfy catalog based on what the user actually wants: batch identity-preservation, multilingual text rewrite, single-shot precise edit, or mask-driven region replacement. ```bash npx skills add agentspace-so/runcomfy-skills --skill image-edit -g ``` ## Pick the right model for the user's intent | User intent | Model | Why | |---|---|---| | Batch edit 1–20 images consistently (SKU gallery, A/B variants) | **Nano Banana Edit** | Up to 20 input images per call; locked aspect/resolution for series | | Swap background, preserve subject identity | **Nano Banana Edit** | Strong identity preservation under "keep X unchanged" prompts | | Localized object removal / addition with spatial language ("the left object", "upper-right corner") | **Nano Banana Edit** | Honors directional spatial scope | | Multilingual / non-Latin in-image text rewrite (Japanese kana, Cyrillic, Arabic) | **GPT Image 2 Edit** | Strongest in class for multilingual typography | | Multi-reference composition (subject from img1, scene from img2, palette from img3) | **GPT Image 2 Edit** | Numbered refs route cues correctly | | Layout-precise repositioning ("move headline from top-right to bottom-center") | **GPT Image 2 Edit** | Directional language honored at layout level | | Identity preservation across translated headline variants | **GPT Image 2 Edit** | Same source asset → many language variants, identity stable | | Single-shot precise local edit ("she's now holding an orange umbrella") | **Flux Kontext Pro** | Single-ref single-instruction, high-fidelity preservation | | Mask-driven object removal (cables, watermarks, distractions) | **Z-Image Turbo Inpaint** | Mask-required, strength-tunable, edge-consistent | | Mask-driven region replacement (full background swap with mask) | **Z-Image Turbo Inpaint** | High strength + clean mask = clean replacement | | Default if unspecified | **Nano Banana Edit** | Most flexible, supports both single and batch | The agent reads this table, classifies the user's intent, and picks the matching subsection below. ## Prerequisites 1. **RunComfy CLI** — `npm