# Nano Banana Edit

> Edita imágenes con Google Nano Banana 2 (endpoint de edición image-to-image) en RunComfy vía `runcomfy run google/nano-banana-2/edit`, con guía sobre cuándo usar GPT Image 2 edit, Flux Kontext o Nano Banana 2 t2i en su lugar.

Fuente: https://skillsagentes.com/skills/prime-skills/runcomfy-agent-skills/nano-banana-edit
Markdown: https://skillsagentes.com/skills/prime-skills/runcomfy-agent-skills/nano-banana-edit.md

Repositorio: https://github.com/prime-skills/runcomfy-agent-skills
Autor: prime-skills
Licencia: MIT
Actualizado: hace 5 meses
Coste de contexto: 137 tok instalada, 2.3k tok al activarse, 2.3k tok con todos los archivos del bundle
Bundle: 1 archivo, 9 KB
Permisos que pide: ninguno declarado

## Instalación

Un skill son archivos markdown: los mismos archivos valen para cualquier agente y lo único que cambia es el directorio de destino, es decir la bandera `--agent`. Añade `-g` para instalarlo en todos los proyectos de la máquina.

```bash
# Claude Code
npx -y skills add prime-skills/runcomfy-agent-skills --skill nano-banana-edit --agent claude-code
# Cursor
npx -y skills add prime-skills/runcomfy-agent-skills --skill nano-banana-edit --agent cursor
# Codex
npx -y skills add prime-skills/runcomfy-agent-skills --skill nano-banana-edit --agent codex
# Gemini CLI
npx -y skills add prime-skills/runcomfy-agent-skills --skill nano-banana-edit --agent gemini
# Windsurf
npx -y skills add prime-skills/runcomfy-agent-skills --skill nano-banana-edit --agent windsurf
# Cline
npx -y skills add prime-skills/runcomfy-agent-skills --skill nano-banana-edit --agent cline
```

## Qué hace

- Ejecuta `runcomfy run google/nano-banana-2/edit` para editar imágenes preservando identidad, cambiando fondos o localizando cambios con lenguaje espacial
- Soporta hasta 20 imágenes de entrada por llamada para ediciones en lote y variación multi-referencia
- Descarga los resultados generados en `--output-dir` sondeando la petición remota

## Cuándo usarla

- El usuario pide explícitamente "nano banana edit", "edit with nano banana" o "image edit nano banana"
- Se necesita preservar identidad del sujeto y cambiar fondo o ropa
- Se requiere editar consistentemente hasta 20 imágenes en un mismo lote
- Se necesita localizar la edición a una zona concreta con lenguaje espacial

## Cuándo no

- Se necesita editar texto multilingüe dentro de la imagen (usar GPT Image 2 edit)
- Se requiere una edición local precisa con una sola referencia (usar Flux Kontext)
- Se quiere generar una imagen nueva desde cero (usar Nano Banana 2 t2i)

## Qué la activa

- "Edita esta imagen con nano banana manteniendo la identidad del sujeto y cambia el fondo a una calle cyberpunk lluviosa"
- "Haz un batch edit de estas 5 fotos de producto con nano banana edit, mismo encuadre"
- "Elimina solo el objeto de la izquierda de esta foto con nano banana edit"
- "Reemplaza el texto de la marca en la etiqueta de "
- "Sustituye el fondo por un estudio gris cálido en estas imágenes de producto"

## Antes de instalar

- Requiere RunComfy CLI (`npm i -g @runcomfy/cli`) y una cuenta RunComfy (`runcomfy login` o `RUNCOMFY_TOKEN` en CI).
- Necesita en el PATH: npx
- makes network requests

## Archivos

- SKILL.md — 9 KB

## SKILL.md

Reproducido tal cual desde prime-skills/runcomfy-agent-skills bajo MIT. Esta sección es el documento original y está en inglés.

# 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 object only"):**

```bash
runcomfy run google/nano-banana-2/edit \
  --input '{
    "prompt": "Remove the leftmost object only. Keep the right two objects, the table, and the lighting unchanged.",
    "image_urls": ["https://.../still-life.jpg"]
  }' \
  --output-dir <absolute/path>
```

## Prompting — what actually works

**Preservation first, change last.** Always lead with `"Keep [identity / pose / clothing / brand / framing] unchanged."` Then state the change in one clean sentence. Models honor what's stated up front; tail-end preservations get ignored.

**Localize with spatial language.** "background only", "the left object", "the upper-right corner", "above the headline" — concrete spatial scopes are honored. "make it more X" is vague and drifts.

**Batch consistency** — when editing a series, lock `aspect_ratio` and `resolution`. Use the same prompt grammar across the batch so each output reads as a sibling, not a remix.

**Iterate small.** If a one-pass edit drifts, split into two: pass 1 changes background only, pass 2 swaps the subject's outfit. Cleaner edits, same total cost (assuming similar resolution).

**Multi-image variation** — pass up to 20 inputs to get a coherent batch. Useful for SKU galleries, A/B testing, character sheet variations.

**Anti-patterns:**
- Long compound instructions ("change A and B and C and D") — drift increases per added scope.
- Edit instructions written in passive voice ("the background should be changed") — be imperative.
- Missing preservation goals — model will subtly rewrite the face / brand.
- Aspect ratios that don't match input — causes crops or stretches.

## Where it shines

| Use case | Why Nano Banana Edit |
|---|---|
| **SKU gallery — same product on different backgrounds** | Batch of 20, identity-preserved, framing locked |
| **Influencer / spokesperson background swaps** | Strong identity preservation across edits |
| **Localized object removal / addition** | Spatial language honored |
| **A/B variants for ad creative** | Seed lock + multiple `number_of_images` |
| **Brand-asset relocalization** | Same composition with text / palette swap |

## Sample prompts (verified to produce strong results)

**Background swap (page example):**

```
Keep the subject identity unchanged. Convert the background into a rainy
neon cyberpunk street.
```

**Targeted text replacement:**

```
Keep the bottle, label, and lighting exactly as in the input.
Replace only the brand text on the label from "ALPHA" to "AURA",
same font weight, centered, white on black.
```

**Multi-image batch consistency:**

```
For each input image: keep the subject's pose and identity unchanged.
Convert the background to a soft warm-grey studio sweep with subtle
floor shadow. Center the subject at the same fraction of frame as the
input.
```

## Limitations

- **1–20 input images per call** — the first is treated as primary; the rest provide auxiliary cues.
- **1–4 outputs per call.**
- **Long compound prompts drift** — split into multiple passes.
- **Web search adds latency + cost** — only enable on demand.
- **For multilingual in-image text edits, GPT Image 2 edit wins.**

## Exit codes

| code | meaning |
|---|---|
| 0  | success |
| 64 | bad CLI args |
| 65 | bad input JSON / schema mismatch |
| 69 | upstream 5xx |
| 75 | retryable: timeout / 429 |
| 77 | not signed in or token rejected |

Full reference: [docs.runcomfy.com/cli/troubleshooting](https://docs.runcomfy.com/cli/troubleshooting?utm_source=skills.sh&utm_medium=skill&utm_campaign=nano-banana-edit).

## How it works

The skill invokes `runcomfy run google/nano-banana-2/edit` with a JSON body matching the schema. The CLI POSTs to `https://model-api.runcomfy.net/v1/models/google/nano-banana-2/edit`, polls the request, fetches the result, and downloads any `.runcomfy.net`/`.runcomfy.com` URL into `--output-dir`. `Ctrl-C` cancels the remote request before exit.

## Security & Privacy

- **Token storage**: `runcomfy login` writes the API token to `~/.config/runcomfy/token.json` with mode 0600 (owner-only read/write). Set `RUNCOMFY_TOKEN` env var to bypass the file entirely in CI / containers.
- **Input boundary**: the user prompt is passed as a JSON string to the CLI via `--input`. The CLI does NOT shell-expand the prompt; it transmits the JSON body directly to the Model API over HTTPS. No shell injection surface from prompt content.
- **Third-party content**: image / mask / video URLs you pass are fetched by the RunComfy model server, not by the CLI on your machine. Treat external URLs as untrusted; image-based prompt injection is a known risk for any image-edit / video-edit model.
- **Outbound endpoints**: only `model-api.runcomfy.net` (request submission) and `*.runcomfy.net` / `*.runcomfy.com` (download whitelist for generated outputs). No telemetry, no callbacks.
- **Generated-file size cap**: the CLI aborts any single download > 2 GiB to prevent disk-fill from a malicious or runaway model output.

## Dónde encaja

- Categoría: [Diseño y UI](https://skillsagentes.com/categorias/diseno-ui.md) — Sistemas de diseño, trabajo con componentes y acabado visual.
- Creador: [prime-skills](https://skillsagentes.com/creators/prime-skills.md) — 30 skills en el directorio
- [Todas las skills](https://skillsagentes.com/skills.md)
- [Ranking de instalaciones](https://skillsagentes.com/ranking.md)

## Otras skills del mismo repositorio

- [Ai Music](https://skillsagentes.com/skills/prime-skills/runcomfy-agent-skills/ai-music.md): Genera música con IA en RunComfy mediante la CLI `runcomfy`, enrutando entre ElevenLabs AI Music Generation (voz premium 44.1 kHz) y ACE Step / ACE Step 1.5 (código abierto, mucho más barato), más inpaint y outpaint de audio.
- [Ace Step](https://skillsagentes.com/skills/prime-skills/runcomfy-agent-skills/ace-step.md): Genera, inpaint y outpaint música con ACE Step de StepFun-AI en RunComfy vía la CLI `runcomfy`: composición por tags, letras multilingües, hasta 4 min, desde $0.0002/s.
- [Video Outpainting](https://skillsagentes.com/skills/prime-skills/runcomfy-agent-skills/video-outpainting.md): Outpainting de video vía el CLI `runcomfy`: extiende el lienzo espacial, cambia la relación de aspecto (9:16 a 16:9 o viceversa) preservando la acción central, usando Wan 2-7 edit-video o flujos ComfyUI dedicados.
- [Video Extend](https://skillsagentes.com/skills/prime-skills/runcomfy-agent-skills/video-extend.md): Extiende o continúa un clip de video existente en RunComfy vía la CLI runcomfy, usando los endpoints extend-video y fast/extend-video de Google Veo 3-1.
- [Image Outpainting](https://skillsagentes.com/skills/prime-skills/runcomfy-agent-skills/image-outpainting.md): Outpainting de imágenes en RunComfy vía el CLI `runcomfy`: extiende el lienzo, cambia el aspect ratio y rellena lo que la cámara no captó, preservando el contenido original.

---

Skills Agentes · [Índice de páginas en markdown](https://skillsagentes.com/sitemap.md) · [Inicio](https://skillsagentes.com/index.md)