Summary
This is an intent router for image editing that picks between four RunComfy models based on what you're actually trying to do. If you're batch-editing a product gallery and need consistent identity preservation, it routes to Nano Banana Edit. If you're rewriting in-image text in Japanese or Arabic, it sends the job to GPT Image 2 Edit. Single-shot precise edits go to Flux Kontext Pro, and mask-driven object removal hits Z-Image Turbo Inpaint. The skill bundles each model's documented prompting patterns so you don't waste iterations on the wrong tool. It's useful if you work across multiple image editing workflows and don't want to remember which model handles multilingual typography versus batch aspect-lock.
Install
npx skills add https://github.com/doany-ai/skills --skill image-edit
