skills.rest
Loringtonian
LoringtonianCOMMUNITY
Explore all skills by this author →
𝕏@loringtonGitHub

nano-banana-flash

Generate 1024x1024 images from text prompts and up to three reference images using Google Gemini 2.5 Flash Image.

12|2|Updated Jun 8, 2026
Search Tags:#image generation#visual design#gemini#prompting#reference images#concept art
One-click install
npx skills add https://github.com/Loringtonian/second-brain-template --skill nano-banana-flash
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nano-banana-flash
Source: https://github.com/Loringtonian/second-brain-template/tree/main/.claude/skills/nano-banana-flash
Command: npx skills add https://github.com/Loringtonian/second-brain-template --skill nano-banana-flash

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill turns text prompts and a small set of reference images into finished visuals quickly, so you can move from idea to image without a slow, complex workflow.

Core Features & Use Cases

  • Fast image generation: Produce 1024x1024 images with Google Gemini 2.5 Flash Image for rapid iteration.
  • Reference-guided creation: Combine up to three reference images with a prompt to steer style, composition, or subject consistency.
  • Batch and concept work: Ideal for quick mockups, social content, thumbnails, and high-volume variations where speed matters.

Quick Start

Use the nano-banana-flash skill to generate a cinematic poster of a glowing robot in a rainy city and open the finished image immediately.

Frequently Asked Questions about nano-banana-flash

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate concept art using text prompts and reference images?▼

Rapid image generation from text prompts and reference images uses Google Gemini 2.5 Flash Image to create 1024x1024 visuals. You provide a descriptive prompt and up to three reference images to guide style, composition, and subject consistency for immediate output.

Can I use reference images to guide the style of generated thumbnails?▼

Yes, reference images can guide the style of generated thumbnails. The process accepts up to three reference images alongside your text prompt to steer the visual style, composition, and subject consistency for your social graphics and batch variations.

Does Gemini 2.5 Flash Image support batch variation tasks for social graphics?▼

Gemini 2.5 Flash Image supports batch variation tasks for social graphics by providing fast image generation. It is designed for high-volume variations and quick mockups where speed matters, outputting 1024x1024 images for rapid visual iteration.

What is the maximum number of reference images I can use for image generation?▼

The maximum number of reference images you can use for image generation is three. You can combine up to three reference images with your text prompt to steer the style, composition, or subject consistency of the final 1024x1024 visual output.

What are the limitations of using rapid image generation for concept art?▼

Limitations of rapid image generation for concept art include a fixed 1024x1024 output resolution and a maximum of three reference images. It is built for lightweight visual generation and high-volume variations rather than complex, slow, or highly detailed workflows.

Related Skills

Explore More Design & Creative Skills→
bahayonghangbahayonghang
16

gemini-image

Generate images from text prompts or reference images via the Gemini API.

Community
Basic
flight505flight505
3

image

Generate and edit images via OpenRouter AI models from Python.

Community
Basic
obulaiobulai
1

obul-nano-banana-2

Generate images from text prompts using Google Gemini 3.1 Flash Image.

Official
Intermediate
jason660519jason660519

stable-diffusion-image-generation

Generate images from descriptive prompts using Stable Diffusion pipelines in Python.

Community
Advanced