Nano Banana Edit
Edit existing images with Google Nano Banana 2 on RunComfy while preserving subject identity and routing to sibling models when edit is wrong fit.
Overview
Nano Banana Edit is an agent skill for the Build phase that runs Google Nano Banana 2 image-to-image edits on RunComfy with up to 20 inputs and clear routing to alternative edit or t2i models.
Install
npx skills add https://github.com/agentspace-so/runcomfy-skills --skill nano-banana-editWhat is this skill?
- Runs `runcomfy run google/nano-banana-2/edit` via local RunComfy CLI
- Preserves subject identity, background swap, and spatial localized edits
- Supports multi-image batch edits with up to 20 input images per call
- Documents when to use GPT Image 2 edit, Flux Kontext, or Nano Banana 2 t2i instead
- Triggers on explicit Nano Banana edit phrases and image-to-image edit requests
- Up to 20 input images per Nano Banana 2 edit call
- Includes model routing table versus GPT Image 2 edit, Flux Kontext, and Nano Banana 2 t2i
Adoption & trust: 25 installs on skills.sh; 2 GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You need subject-faithful image edits via API but do not know which RunComfy endpoint, CLI flags, or sibling model fits background swap versus full redraw.
Who is it for?
Solo builders automating marketing or in-app image edits through RunComfy when preserving identity and batch multi-reference edits matter.
Skip if: Pure text-to-image generation without source images, workflows with no RunComfy CLI or API access, or edits explicitly requested on a different vendor model.
When should I use this skill?
Triggers on "nano banana edit", "edit with nano banana", "image edit nano banana", or any explicit request to edit images with this RunComfy model.
What do I get? / Deliverables
The agent invokes the documented Nano Banana 2 edit command with the right inputs and defers to GPT Image 2, Flux Kontext, or t2i when the comparison table says so.
- Executed `runcomfy run google/nano-banana-2/edit` with documented parameters
- Model choice rationale when routing away to GPT Image 2, Flux Kontext, or t2i
Recommended Skills
Journey fit
Image-to-image editing is a Build integration task once you have assets and an API host—not validate landing pages or launch distribution. Integrations subphase matches RunComfy CLI calls, model endpoint choice, and batch multi-image edit workflows against GPT Image 2 or Flux Kontext.
How it compares
Model-specific RunComfy integration skill—not a general prompt library; use Nano Banana 2 t2i or other edit endpoints when the built-in vs-siblings table says edit is wrong.
Common Questions / FAQ
Who is nano-banana-edit for?
Indie developers and agent builders wiring RunComfy image edit into apps or content pipelines who want Nano Banana 2 Edit documented with CLI and routing rules.
When should I use nano-banana-edit?
During Build integrations when you have input images and phrases like nano banana edit, image edit nano banana, or explicit asks to edit with this Gemini-family flash-tier model on RunComfy.
Is nano-banana-edit safe to install?
Check the Security Audits panel on this Prism page; the skill drives external RunComfy API calls and local CLI execution—scope network and shell permissions accordingly.
SKILL.md
READMESKILL.md - Nano Banana Edit
# Nano Banana Edit — Pro Pack on RunComfy [runcomfy.com](https://www.runcomfy.com/?utm_source=skills.sh&utm_medium=skill&utm_campaign=nano-banana-edit) · [Edit endpoint](https://www.runcomfy.com/models/google/nano-banana-2/edit?utm_source=skills.sh&utm_medium=skill&utm_campaign=nano-banana-edit) · [GitHub](https://github.com/agentspace-so/runcomfy-skills/tree/main/nano-banana-edit) Google **Nano Banana 2 Edit** — the image-to-image edit endpoint of the Gemini-family flash-tier image model — hosted on the **RunComfy Model API**. Up to **20 input images per call** for batch edits and multi-reference variation. ```bash npx skills add agentspace-so/runcomfy-skills --skill nano-banana-edit -g ``` ## When to pick this model (vs siblings) | You want | Use | |---|---| | Preserve subject identity, swap background or clothing | **Nano Banana Edit** | | Edit up to 20 images consistently in one batch | **Nano Banana Edit** | | Localize edit to "X only" with spatial language | **Nano Banana Edit** | | Edit multilingual text inside the image (signs, labels) | GPT Image 2 edit | | Single ref + precise local edit ("she's now holding X") | Flux Kontext | | Generate a new image from scratch | Nano Banana 2 t2i (sibling skill) | If the user said "nano banana edit" / "edit with nano banana" explicitly, route here regardless. ## Prerequisites 1. **RunComfy CLI** — `npm i -g @runcomfy/cli` 2. **RunComfy account** — `runcomfy login` opens a browser device-code flow. 3. **CI / containers** — set `RUNCOMFY_TOKEN=<token>` instead of `runcomfy login`. ## Endpoints + input schema ### `google/nano-banana-2/edit` | Field | Type | Required | Default | Notes | |---|---|---|---|---| | `prompt` | string | yes | — | Edit instruction. Lead with preservation, end with the change. | | `image_urls` | array | yes | — | **1–20** publicly-fetchable HTTPS URLs. | | `number_of_images` | int | no | 1 | 1–4 outputs per call. | | `seed` | int | no | — | Reproducibility. | | `aspect_ratio` | enum | no | `auto` | `auto` (follows input) or fixed ratios — lock for batch consistency. | | `resolution` | enum | no | `1K` | `0.5K` / `1K` / `2K` / `4K`. | | `output_format` | enum | no | `png` | `png` / `jpeg` / `webp`. | | `safety_tolerance` | int | no | 4 | 1 (strict) – 6 (permissive). | | `limit_generations` | bool | no | — | If true, restricts each round to one output. | | `enable_web_search` | bool | no | false | Web grounding (extra cost / latency). | ## How to invoke **Single-image background swap, identity preserved:** ```bash runcomfy run google/nano-banana-2/edit \ --input '{ "prompt": "Keep the subject identity, pose, and clothing unchanged. Convert the background into a rainy neon cyberpunk street.", "image_urls": ["https://.../portrait.jpg"] }' \ --output-dir <absolute/path> ``` **Batch edit with locked framing:** ```bash runcomfy run google/nano-banana-2/edit \ --input '{ "prompt": "Replace the watermark in the bottom-right with the text \"AURA\" in clean white sans-serif. Keep everything else exactly as in the input.", "image_urls": ["https://.../sku-1.jpg", "https://.../sku-2.jpg", "https://.../sku-3.jpg"], "aspect_ratio": "1:1", "resolution": "1K" }' \ --output-dir <absolute/path> ``` **Targeted spatial edit ("left