image-edit
🎯Skillfrom prime-skills/runcomfy-agent-skills
Installation
npx vibeindex add prime-skills/runcomfy-agent-skills --skill image-editnpx skills add prime-skills/runcomfy-agent-skills --skill image-edit~/.claude/skills/image-edit/SKILL.md
|A smart intent-routing skill for image editing on RunComfy that selects the optimal model from Nano Banana Edit (batch up to 20 images), GPT Image 2 Edit (multilingual text rewrite, multi-ref composition), Flux Kontext Pro (single-shot precise local edit), or Z-Image Turbo Inpaint (mask-driven region edit) based on user intent.
Overview
Image Edit is an intent-routing skill for the RunComfy platform that automatically selects the best image editing model based on what the user wants to accomplish. It supports four distinct editing routes: Nano Banana Edit for batch processing up to 20 images with identity preservation, GPT Image 2 Edit for multilingual in-image text rewrites and multi-reference compositions, Flux Kontext Pro for single-shot precise local edits with high fidelity, and Z-Image Turbo Inpaint for mask-driven object removal and region replacement. Each route includes optimized prompting patterns and model-specific best practices.
Key Features
- Nano Banana Edit route: Batch edit 1-20 images consistently with identity preservation, supporting resolutions from 0.5K to 4K, spatial scope editing, and aspect ratio locking for series consistency
- GPT Image 2 Edit route: Strongest multilingual in-image typography (Japanese kana, Cyrillic, Arabic), multi-reference composition with up to 10 image inputs, and layout-precise repositioning
- Flux Kontext Pro route: Single-image, single-instruction local edits with high-fidelity preservation for changes like adding objects, modifying details, or adjusting expressions
- Z-Image Turbo Inpaint route: Mask-required precision editing with tunable strength (0.3-1.0) for anything from subtle retouching to full region replacement, with edge-consistent blending
- Automatic intent classification: Analyzes user requests to determine the optimal model without manual selection
- Consistent prompting framework: All routes follow preservation-first prompting where users state what to keep unchanged before describing the desired change
Who is this for?
- E-commerce teams needing batch-consistent edits across product image galleries with locked aspect ratios and resolutions
- Localization teams producing multilingual marketing assets with translated in-image headlines across Japanese, Cyrillic, Arabic, and other scripts
- Photo editors and retouchers who need mask-driven precision for object removal, background replacement, or localized region edits
Same repository
prime-skills/runcomfy-agent-skills(25 items)
SKILL.md
More from this repository10
A smart intent-routing skill for video editing on RunComfy that automatically selects the best model (Wan 2.7 Edit-Video, Kling 2.6 Pro Motion Control, or Lucy Edit Restyle) based on what the user wants to do, from general restyling and background swaps to precise motion transfer and outfit changes.
A smart intent-routing skill that animates still images on RunComfy by selecting the optimal model: HappyHorse 1.0 I2V for general portrait and product animation with native audio, Wan 2.7 for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal composition with image, video, and audio references.
A skill for generating images with Google Nano Banana 2, the flash-tier text-to-image model in the Gemini family on RunComfy, optimized for rapid iteration, batch ideation, in-image typography rendering, and optional web-grounded context with support for resolutions from 0.5K to 4K.
A Claude Code skill that enables precise single-image editing using Black Forest Labs's Flux 1 Kontext Pro model through the RunComfy CLI, with built-in prompting patterns for high-fidelity local edits.
A skill for generating text-to-video with Wan 2.7, Wan-AI's flagship motion model on RunComfy, featuring multi-reference conditioning, audio-driven lip-sync via custom audio tracks, smooth transition physics, prompt expansion control, and up to 1080p output at 15 seconds duration.
A Claude Code skill for generating text-to-video clips with HappyHorse 1.0 via the RunComfy CLI. HappyHorse 1.0 is currently ranked #1 on the Artificial Analysis Video Arena, producing native 1080p video with in-pass synchronized audio and multi-shot character consistency.
A Claude Code skill for generating video with Kling 3.0 via the RunComfy CLI. Covers all six Kling 3.0 endpoints across three rendering tiers (Standard, Pro, 4K) and two modes (text-to-video, image-to-video), with native synchronized audio and multi-shot character consistency.
A Claude Code skill that generates custom OpenAI Codex Pets from a single reference image via the RunComfy CLI. It produces a Codex-compatible spritesheet (1536x1872, 8 columns x 9 rows) and pet.json manifest using GPT Image 2 and ImageMagick, without requiring Codex Pro or an OPENAI_API_KEY.
A Claude Code skill that acts as a smart router for AI video generation across the full RunComfy model catalog. Supports text-to-video, image-to-video, and video-extend modes with models including HappyHorse 1.0, Kling 3.0, Wan 2.7, Seedance, Veo 3.1, and more.
A Claude Code skill that acts as a smart router for AI image generation and editing across 11+ models on the RunComfy platform. Supports text-to-image and image-to-image modes with models including FLUX 2, GPT Image 2, Seedream 5, Nano Banana 2, and more.