What problem does it solve? Editing images programmatically—swapping backgrounds, removing objects, or batch-editing product photos—normally requires manual design work or complex model setup. This Skill routes image-edit requests to Google's Nano Banana 2 edit endpoint hosted on RunComfy, handling identity preservation, spatial localization, and batch consistency through a single CLI call. ## Core Features & Use Cases - Identity-preserving edits: Swap backgrounds or clothing while keeping subject identity, pose, and framing unchanged. - Batch editing up to 20 images: Apply consistent edits across SKU galleries or ad creative variants with locked aspect ratio and resolution. - Spatially localized edits: Target changes with language like "the left object only" or "background only" for precise object removal or text replacement. - Use Case: An e-commerce team needs the same product shot on 20 different backgrounds. Pass all image URLs in one call with a locked 1:1 aspect ratio and receive a coherent, identity-preserved batch. ## Quick Start Ask the AI to edit an image with Nano Banana, for example: use nano banana edit to keep the subject unchanged and convert the background of this portrait into a rainy neon cyberpunk street.
