skills.rest
brillianodhiya
brillianodhiyaCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

image-edit

Routes image editing requests to RunComfy models based on user intent.

Updated Jun 11, 2026
Search Tags:#cli#image editing#model routing#image-to-image#inpainting#batch edit#runcomfy
One-click install
npx skills add https://github.com/brillianodhiya/VisionScript --skill image-edit-brillianodhiya
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: image-edit
Source: https://github.com/brillianodhiya/VisionScript/tree/main/.agents/skills/image-edit
Command: npx skills add https://github.com/brillianodhiya/VisionScript --skill image-edit-brillianodhiya

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @runcomfy/cli.

What problem does it solve? Choosing the wrong image-edit model wastes iterations and credits. This Skill classifies the user's editing intent and routes it to the right model in the RunComfy catalog, with each model's documented prompting patterns bundled in. ## Core Features & Use Cases - Intent-based model routing: Matches requests to Nano Banana Edit (batch up to 20 images, identity preservation), GPT Image 2 Edit (multilingual in-image text, multi-reference composition), Flux Kontext Pro (single-shot local edits), or Z-Image Turbo Inpaint (mask-driven region edits). - Bundled prompting patterns: Each route includes schema tables, preservation-first prompting tips, and strength/size guidance so edits succeed with fewer retries. - CLI execution: Invokes runcomfy run <vendor>/<model>/edit through the local RunComfy CLI with JSON input bodies and an output directory. - Use Case: A user asks to swap the background on 15 product photos while keeping the products identical. The Skill routes to Nano Banana Edit, locks aspect ratio and resolution for batch consistency, and runs one CLI call. ## Quick Start Ask the agent to edit an image, for example: "Remove the watermark from these three product photos and keep everything else unchanged."

Frequently Asked Questions about image-edit

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I edit images with the RunComfy CLI?▼

Install the CLI with npm i -g @runcomfy/cli, run runcomfy login, then call runcomfy run <vendor>/<model>/edit with a JSON --input body containing your prompt and image URLs, plus an --output-dir for results.

Which image edit model should I use for batch editing?▼

Nano Banana Edit handles batch editing of 1 to 20 images per call and is the default for general edits. Lock aspect_ratio and resolution across the batch for consistent output.

What model works best for rewriting text inside an image?▼

GPT Image 2 Edit is strongest for in-image text rewrites, especially multilingual scripts like Japanese kana, Cyrillic, or Arabic. Quote the new text exactly and name the script in the prompt.

Can I edit multiple images with Flux Kontext Pro?▼

No, Flux Kontext Pro accepts only a single source image per call. For multi-image or batch flows, use Nano Banana Edit, which supports up to 20 input images.

How do I remove an object from a specific region of an image?▼

Use Z-Image Turbo Inpaint with a grayscale mask URL where white marks the region to inpaint. Set strength around 0.3-0.5 for retouching or 0.8-1.0 for full region replacement.

What are the limitations of intent-routed image editing?▼

Each route inherits its model's limits: Nano Banana takes 1-20 inputs, GPT Image 2 Edit up to 10 references with four fixed sizes, Flux Kontext a single image, and Z-Image requires a mask. Only one model runs per call.

Related Skills

Explore More Design & Creative Skills→
genmedia-labsgenmedia-labs
12

image-edit

Routes image editing requests to RunComfy models based on user intent.

Official
Intermediate
mohammedburqanmohammedburqan

email-promo

Generate promotional email copy with A/B subject line variants using RMBC methodology.

Community
Advanced
syl2042syl2042

image-enhancer

Upscale, sharpen, and reduce compression artifacts in image files.

Community
Intermediate
igniteenowigniteenow
16

comfyui

Generate images, video, and audio by executing ComfyUI diffusion workflows via REST and WebSocket APIs.

Community
Advanced