Image Edit
Route natural-language image edits through the RunComfy CLI to the right catalog model for backgrounds, objects, inpainting, or in-image text without trial-and-error model picking.
Overview
Image Edit is an agent skill most often used in Build—integrations (also Launch distribution and Grow content) that routes your edit intent to the right RunComfy image-edit model and runs it via the local CLI.
Install
npx skills add https://github.com/agentspace-so/runcomfy-agent-skills --skill image-editWhat is this skill?
- Smart router among Nano Banana Edit (batch up to 20), GPT Image 2 Edit, Flux Kontext Pro, and Z-Image Turbo Inpaint
- Bundles per-model prompting patterns to reduce wasted iterations
- Covers background swap, object removal, mask inpainting, multilingual in-image text rewrite, and multi-reference composi
Adoption & trust: 210k installs on skills.sh; 15 GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You know what to change in an image but waste iterations picking the wrong RunComfy edit model or weak prompts for batch, inpaint, or in-image text jobs.
Who is it for?
Solo builders with RunComfy CLI access who need routed i2i edits (background swap, object removal, inpainting, or headline rewrites) from inside an agent session.
Skip if: Teams that need a self-hosted editor with no external API, pure text-to-image from scratch only, or pixel-perfect retouching without generative models.
When should I use this skill?
User asks to image edit, edit image, image-to-image, i2i, swap background, remove object, rewrite headline, or explicitly edit one or a batch of images via RunComfy.
What do I get? / Deliverables
You get a CLI-backed edit run on a matched RunComfy model with prompting patterns tuned to your scenario—batch identity preservation, mask inpaint, Kontext fidelity, or GPT Image 2 text and layout edits.
- Executed RunComfy edit job for the selected vendor/model
- Edited image output from the chosen pipeline
- Documented model choice and prompt pattern used for the intent
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Canonical shelf is Build because solo builders most often wire generative edits while assembling product visuals, mocks, and campaign assets—not as a one-off launch-only trick. Integrations fits best: the skill’s core is invoking `runcomfy run <vendor>/<model>/edit` and model selection, not hand-coding a frontend image pipeline.
Where it fits
Batch-update app store screenshots with identity-preserving variants via Nano Banana Edit before shipping a UI refresh.
Locally refine a hero mock with Flux Kontext Pro after a design pass without leaving the agent terminal.
Swap campaign backgrounds and rewrite in-image headlines with GPT Image 2 Edit for launch social assets.
Mask-remove a distracting object from a blog hero using Z-Image Turbo Inpaint during a content refresh.
How it compares
Use as an agent skill that picks RunComfy catalog edit models and CLI invocations—not as a generic chat img2img guess or a local-only image library.
Common Questions / FAQ
Who is Image Edit for?
Image Edit is for solo and indie builders using Claude Code, Cursor, Codex, or similar agents who already work with RunComfy and want dependable image-to-image edits without manually comparing four edit endpoints.
When should I use Image Edit?
Use it during Build when you are assembling UI shots, mock assets, or batch variants; at Launch when you need distribution-ready visuals with swapped backgrounds or rewritten in-image copy; and during Grow when you refresh content images, remove distractions, or inpaint specific
Is Image Edit safe to install?
Treat it like any skill that shells out to a CLI and calls hosted models: review the Security Audits panel on this Prism page, confirm RunComfy and network usage fit your policy, and avoid sending sensitive assets you would not upload to a third-party image API.
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