skills.rest
roberto-mello
roberto-melloCOMMUNITY
Explore all skills by this author →
Website𝕏@robertobmelloGitHub

gemini-imagegen

Generate and refine images via the Gemini API with configurable resolutions.

50|2|Updated Feb 8, 2026
Search Tags:#gemini#image-generation#prompt-engineering#image-editing#ai-art#multiturn
One-click install
npx skills add https://github.com/roberto-mello/beads-compound-plugin --skill gemini-imagegen-roberto-mello
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gemini-imagegen
Source: https://github.com/roberto-mello/beads-compound-plugin/tree/main/plugins/beads-compound/gemini/skills/gemini-imagegen
Command: npx skills add https://github.com/roberto-mello/beads-compound-plugin --skill gemini-imagegen-roberto-mello

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Gemini Image Generation enables generating and refining images via the Gemini API for a wide range of visual tasks, including text-to-image creation, editing existing images, style transfers, and branding assets like logos and product mockups.

Core Features & Use Cases

  • Text-to-Image: Create images from prompts with configurable resolution and aspect ratio.
  • Image Editing: Iterate on existing images with multi-turn refinement and semantic edits.
  • Branding & Assets: Generate logos, stickers, and product mockups with text integration and style transfer.
  • Composition: Combine elements from multiple reference images into a cohesive result.

Quick Start

Generate a 1:1 logo for 'Gemini Labs' with a blue gradient and finalize with a single refinement pass.

Frequently Asked Questions about gemini-imagegen

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

FAQPage Schema
How do I generate and refine images from text prompts using the Gemini API?▼

To generate and refine images using the Gemini API, you apply text-to-image prompts to the gemini-3-pro-image-preview model with configurable resolutions and aspect ratios, supporting multi-turn refinement for iterative edits.

Can I use Gemini AI for style transfers and product mockups?▼

Yes, you can use Gemini AI for style transfers and product mockups by applying semantic edits and combining elements from multiple reference images into cohesive branding assets like logos and stickers.

Do I need a specific API key to perform text-to-image generation with Gemini?▼

Yes, text-to-image generation with Gemini requires a valid GEMINI_API_KEY to authenticate requests to the gemini-3-pro-image-preview model for your visual design tasks.

How does multi-turn image editing work with Gemini?▼

Multi-turn image editing with Gemini works by iterating on existing images through successive semantic edits, allowing you to refine details and apply style transfers across multiple interaction cycles.

What is the best way to create a logo with Gemini image generation?▼

The best way to create a logo with Gemini image generation is to provide a text-to-image prompt specifying design elements, then use multi-turn refinement to finalize the composition with your desired resolution and aspect ratio.

Are there limitations when combining multiple reference images in Gemini?▼

When combining multiple reference images in Gemini, the model relies on semantic edits to compose elements into a cohesive result, meaning complex compositions may require several multi-turn refinement passes to achieve the desired output.

Related Skills

Explore More Design & Creative Skills→
nicepkgnicepkg
276

nano-banana-pro

Generate and edit images using Google's gemini-3-pro-image-preview model.

Official
Intermediate
yxc023yxc023

gemini-imagegen

Generate and edit images using the Gemini API from text prompts and references.

Community
Advanced
shenxingyshenxingy
8

banana

Generate and edit images via prompt-engineered Gemini Nano Banana requests.

Community
Advanced
IAmKongHaiIAmKongHai

ce-gemini-imagegen

Generate and edit images using Google's Gemini API.

Community
Advanced