gemini-image

Generate images from text prompts or image URLs via a configurable AI API.

1|Updated May 12, 2026
One-click install
npx skills add https://github.com/cocyuhao/my-ai-skills-library --skill gemini-image-cocyuhao
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gemini-image
Source: https://github.com/cocyuhao/my-ai-skills-library/tree/main/gemini-image
Command: npx skills add https://github.com/cocyuhao/my-ai-skills-library --skill gemini-image-cocyuhao

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

在无需深度绘画技能的情况下,通过文本描述或图像参考快速生成高质量图像,提升创作效率与迭代速度。

Core Features & Use Cases

  • 文生图:基于描述文本生成目标图像,支持多风格与主题。
  • 图生图:使用图片URL和描述实现风格迁移或风格融合的图像生成。
  • 多图参考:结合多张参考图片与文本描述实现个性化视觉效果。
  • 使用场景:为产品视觉、海报草图、概念艺术等场景提供快速一键生成能力。

Quick Start

直接输入文本描述即可生成图像。

Frequently Asked Questions about gemini-image

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

FAQPage Schema
How do I generate images from text descriptions for concept art?

To generate images from text, input your descriptive prompt directly. The AI API translates your text into high-quality visuals for concept art and marketing materials.

Can I use reference images to guide AI image generation and style transfer?

Yes, you can perform image-to-image generation by providing image URLs alongside text prompts. This enables style transfer and visual fusion based on your reference images.

Do I need an API key to use text-to-image generation?

Yes, API access is required to process text-to-image and image-to-image workflows. You must configure the API connection before generating marketing visuals or product imagery.

What is the best way to create product visuals using AI art?

The best way to create product visuals is combining multiple reference image URLs with text descriptions. This multi-image reference approach yields personalized marketing visuals quickly.

Does AI image generation support multiple reference images for personalized results?

Yes, the generation workflow supports combining multiple reference images with text descriptions. This applies to creative tasks requiring personalized visual effects and style fusion.