Nano Banana Pro
- 279 repo stars
- Updated April 25, 2026
- intellectronica/agent-skills
nano-banana-pro is an agent skill that generates and edits images via Google’s Nano Banana Pro (Gemini 3 Pro Image) API.
About
nano-banana-pro is an agent skill that wires your coding agent to Google’s Nano Banana Pro (Gemini 3 Pro Image) API for both creating images from prompts and editing existing files. Developers use it when they need hero shots, social graphics, UI concept art, or quick variants without leaving the agent thread. Triggers match natural language asks to generate, create, edit, modify, change, alter, or update images, including when the user points at an on-disk image and wants background swaps or object replacements. The workflow favors passing --input-image directly rather than pre-reading binary assets, which keeps token use down and matches the skill’s documented guardrail. Resolution can be tuned for default 1K delivery or sharper 2K and 4K exports when you are shipping landing pages or store assets. It is a task integration, not a full creative pipeline—you still own brand consistency, licensing, and prompt safety review before publishing.
- Text-to-image generation via Nano Banana Pro (Gemini 3 Pro Image)
- Image-to-image edits with --input-image (modify background, replace elements)
- Configurable output resolution: 1K default, 2K, or 4K
- Explicit flow: do not read the source image file first—call the skill with --input-image
Nano Banana Pro by the numbers
- Data as of Jul 20, 2026 (Skillselion catalog sync)
/plugin marketplace add intellectronica/agent-skills/plugin install nano-banana-pro@intellectronica-skillsAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| repo stars | ★ 279 |
|---|---|
| Last updated | April 25, 2026 |
| Repository | intellectronica/agent-skills ↗ |
What it does
Generate or edit marketing and product visuals through Google’s Nano Banana Pro image API without manually opening files in the agent first.
Who is it for?
Best when you want fast API-driven image generation and edits from Claude Code, Cursor, or similar agents during product and content work.
Skip if: Skip if you require on-prem-only media, strict data-residency bans on cloud image APIs, or fully offline asset pipelines without external API calls.
When should I use this skill?
User asks to generate, create, edit, modify, change, alter, or update images, or references an existing image file to modify (use --input-image; do not read the image file first).
What you get
The agent produces or updates image assets at 1K, 2K, or 4K resolution using text prompts or --input-image edits without reading the source image into context first.
- Generated or edited image files at chosen resolution (1K, 2K, or 4K)
- API-driven image variants from text or --input-image prompts
By the numbers
- Three resolution modes: 1K default, 2K, and 4K
- Supports both text-to-image and image-to-image editing
Files
Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.
nano-banana-pro
Source: ./plugins/nano-banana-pro
{ "name": "nano-banana-pro", "source": "./plugins/nano-banana-pro", "version": "0.1.1768936949", "category": "media", "description": "Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., \"modify this image\", \"change the background\", \"replace X with Y\"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter." }
Related skills
Remotion Best PracticesGet Remotion-specific coding guidance that prevents common video rendering mistakes when creating animated React videos.442k4.1k
Remotion RenderGenerate high-quality MP4 videos from React code using Remotion inside an AI coding agent.363k648Ai Video GenerationTurn written prompts into short videos using AI video generation models directly from Cursor or Claude.363k648Ai Avatar VideoGenerate short talking-head videos of custom AI avatars from text prompts.363k648Ai Image GenerationLet their coding agent generate, iterate on, and insert high-quality images directly into web apps, marketing assets, or product features.363k648
Video EditIntelligently route video editing requests to the best RunComfy model without trial-and-error.357k31How it compares
Use as a focused Gemini image API skill rather than generic chat image requests without resolution and --input-image conventions.
FAQ
Who is nano-banana-pro for?
Developers shipping sites, apps, or content who want agent-triggered image generation and edits through Google’s Nano Banana Pro API.
When should I use nano-banana-pro?
Use it in Build (frontend visuals, docs illustrations) and in Launch/Grow when you need campaign or social images; invoke whenever the user asks to generate, create, edit, modify, change, alter, or update images, including modifying an existing file via --input-image.
Is nano-banana-pro safe to install?
Review the Security Audits panel on this Prism page and confirm API keys, billing, and data handling for Google image services before enabling network access in your agent.