nano-banana-edit

What problem does it solve?

It solves the problem of performing high-quality image-to-image edits (like background swaps or localized object changes) while preserving the subject’s identity across one or many reference images.

Core Features & Use Cases

• Identity-preserving edits: Keep subject identity, pose, and key appearance traits stable while changing the intended elements.
• Localized spatial targeting: Apply changes to specific regions using concrete spatial language (e.g., “left object only”, “upper-right corner”).
• Multi-image batch consistency: Edit up to 20 input images per call with locked framing via consistent aspect ratio and resolution.
• When to route vs siblings: Use this for Nano Banana 2 edit scenarios; prefer siblings for text-in-image edits (GPT Image 2 edit), single-ref precise local edits (Flux Kontext), or pure generation (Nano Banana 2 t2i).

Quick Start

Use the nano-banana-edit skill to swap the background of a portrait while keeping the subject identity unchanged by prompting: "Keep the subject identity, pose, and clothing unchanged; convert the background into a rainy neon cyberpunk street."