gemini-imagegen

Generate and edit images using the Gemini API with configurable aspect ratios.

1|Updated Jan 11, 2025
One-click install
npx skills add https://github.com/krbylit/dotfiles --skill gemini-imagegen-krbylit
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gemini-imagegen
Source: https://github.com/krbylit/dotfiles/tree/main/cm-util/pkg-backups/beads-compound/0.6.8/gemini/skills/gemini-imagegen
Command: npx skills add https://github.com/krbylit/dotfiles --skill gemini-imagegen-krbylit

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Generate and edit images efficiently using the Gemini API, simplifying complex visual tasks from prompts and image inputs.

Core Features & Use Cases

  • Generate images from text prompts with configurable resolution and aspect ratios.
  • Edit existing images with iterative refinements and multi-turn prompts.
  • Create logos, stickers, product mockups, and stylized art by combining references.

Quick Start

Provide a text prompt or reference images to generate or edit an image using the Gemini API.

Frequently Asked Questions about gemini-imagegen

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

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

To generate images from text prompts using the Gemini API, provide your prompt to the default gemini-3-pro-image-preview model. The Skill outputs images at 1K resolution with a default 1:1 aspect ratio.

Can I edit existing images and apply multi-turn refinements with Gemini AI?

Yes, you can edit existing images with Gemini AI by supplying reference image inputs. The Skill supports iterative multi-turn refinement, allowing you to apply successive prompt adjustments to reach your desired visual output.

Do I need a GEMINI_API_KEY to generate logos and product mockups?

Yes, you need a valid GEMINI_API_KEY to generate logos, product mockups, and stickers. This key authenticates your requests to Google's Gemini API for processing both text-to-image generation and image editing workflows.

What aspect ratios are supported when generating images with the Gemini API?

Generating images with the Gemini API supports multiple aspect ratios including 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, and 21:9. You can configure these dimensions alongside the default 1K resolution output.

How does combining multiple reference images work for stylized art generation?

Combining multiple reference images for stylized art generation works by feeding several image inputs into the Gemini API alongside your text prompt. The AI synthesizes the visual characteristics of the references to create customized logos, stickers, or artistic outputs.

What is the default resolution for AI image generation with this Gemini workflow?

The default resolution for AI image generation with this Gemini workflow is 1K. This applies to the default gemini-3-pro-image-preview model across all supported aspect ratios when creating or editing images from prompts.