gemini-3-pro-imagegen

Generate and edit images using Gemini Nano Banana Pro and Nano Banana 2 models.

68|29|Updated Jan 26, 2026
One-click install
npx skills add https://github.com/revfactory/skills --skill gemini-3-pro-imagegen
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gemini-3-pro-imagegen
Source: https://github.com/revfactory/skills/tree/main/gemini-3-pro-imagegen
Command: npx skills add https://github.com/revfactory/skills --skill gemini-3-pro-imagegen

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai, Pillow, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Generating high-quality Gemini-based images from prompts and editing existing visuals to accelerate creative workflows.

Core Features & Use Cases

  • Text-to-image generation with Gemini Nano Banana Pro and Nano Banana 2 models, including grounding options.
  • Image editing and multi-turn refinements using natural prompts.
  • Grounding with Google search for real-time visuals and multi-reference composition.

Quick Start

Provide a descriptive prompt and optional reference images to generate high-quality Gemini images.

Frequently Asked Questions about gemini-3-pro-imagegen

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

FAQPage Schema
How do I generate high-quality images from text prompts using Gemini models?

To generate high-quality images from text prompts using Gemini, provide a descriptive prompt and optional reference images. This Skill leverages Gemini Nano Banana Pro and Nano Banana 2 models for text-to-image generation and supports multi-turn refinement.

Can I edit existing images and refine them through multi-turn interaction?

Yes, you can edit existing images and refine them through multi-turn interaction using natural prompts. This allows iterative visual adjustments for logos, product mockups, and visual storytelling without restarting the generation process.

Does Gemini image generation support Google search grounding for real-time visuals?

Gemini image generation supports optional Google search grounding to fetch real-time visuals. This feature enables multi-reference composition, ensuring generated images are factually grounded and contextually accurate based on current search results.

What can I create with Gemini text-to-image generation beyond basic photos?

Gemini text-to-image generation creates premium visuals for diverse use cases including logos, infographics, product mockups, comics, and visual storytelling. It handles complex compositions and multi-turn refinements for specialized creative workflows.

Do I need specific Gemini models to generate and edit images?

Yes, generating and editing images requires specific Gemini models, namely Nano Banana Pro and Nano Banana 2. These models facilitate the text-to-image generation, image editing, and multi-turn interaction capabilities described.

How do I use reference images to guide Gemini image generation?

To use reference images for guiding Gemini image generation, provide them alongside your descriptive text prompt. This enables multi-reference composition, allowing the models to blend your visual inputs with text instructions for targeted output.