skills.rest
bahayonghang
bahayonghangCOMMUNITY
Explore all skills by this author →
GitHub

gemini-image

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

16|1|Updated Jan 2, 2026
Search Tags:#gemini#image-generation#generate#text-to-image#image-to-image#prompt#ai-art
One-click install
npx skills add https://github.com/bahayonghang/my-claude-code-settings --skill gemini-image-bahayonghang
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gemini-image
Source: https://github.com/bahayonghang/my-claude-code-settings/tree/main/skills/gemini-image
Command: npx skills add https://github.com/bahayonghang/my-claude-code-settings --skill gemini-image-bahayonghang

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill enables rapid creation of AI-generated imagery from textual prompts or image references, accelerating concept art, design exploration, and visual content production.

Core Features & Use Cases

  • Text-to-Image generation from descriptive prompts to produce concept art, illustrations, or marketing visuals.
  • Image-to-Image generation to apply styles or modify an existing image using prompts or reference images.
  • Multi-Reference and Style Transfer to blend influences from several images for a cohesive result.
  • Use Case: Imagine you need a futuristic cityscape illustration; describe the scene and style, and the skill returns a ready-to-use image URL.

Quick Start

Read API configuration from config/secrets.md, construct an appropriate prompt, call the Gemini image generation API, and return the generated image URL.

Frequently Asked Questions about gemini-image

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

FAQPage Schema
How do I generate AI art from text prompts?▼

To generate AI art from text prompts, you provide a descriptive plain text prompt and the skill returns a ready-to-use image URL. This text-to-image workflow produces concept art, illustrations, or marketing visuals directly from your descriptions.

Can I use an image reference for style transfer?▼

Yes, you can use an image reference for style transfer through the image-to-image workflow. By providing an image URL alongside your prompt, the skill modifies the existing image or blends influences from multiple reference images for a cohesive result.

Do I need a Gemini API key to generate images?▼

Yes, you need a configured Gemini API key to generate images. The skill reads this API configuration from config/secrets.md to authorize requests to the Gemini image generation API and return the resulting image URL.

What is the best way to create concept art from a description?▼

The best way to create concept art from a description is using a text-to-image generation workflow. You construct a detailed prompt describing the desired scene and style, and the skill returns a ready-to-use image URL for your visual content.

What input formats are supported for image-to-image generation?▼

For image-to-image generation, the skill accepts prompts as plain text or image URLs. This allows you to apply styles or modify existing images by combining textual descriptions with reference image URLs.

Related Skills

Explore More Design & Creative Skills→
kienhaminhkienhaminh

gemini-image-gen

Generate and edit images from text prompts using Gemini 2.5 Flash Image.

Community
Advanced
zerwizzerwiz

gif-search

Search Tenor and download GIFs with curl and jq.

Community
Basic
wanyusheng63-altwanyusheng63-alt

generate-image-by-image

Edit existing images via Tencent Hunyuan's generate-image-by-image API.

Community
Intermediate
eykdeykd

generate-image

Generate and edit images using Gemini 2.5 with text prompts.

Community
Intermediate