skills.rest
vaayne
vaayneCOMMUNITY
Explore all skills by this author →
Website𝕏@LiuVaayneGitHub

vertex-ai-image

Generate, edit, and describe images using Google Gemini models via CLI.

52|4|Updated Oct 23, 2025
Search Tags:#editing#image#cli#gemini#generate#describe#google-genai
One-click install
npx skills add https://github.com/vaayne/agent-kit --skill vertex-ai-image
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: vertex-ai-image
Source: https://github.com/vaayne/agent-kit/tree/main/skills/vertex-ai-image
Command: npx skills add https://github.com/vaayne/agent-kit --skill vertex-ai-image

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Generate, edit, and describe images using Google Gemini models, streamlining visual content creation and refinement.

Core Features & Use Cases

  • Generate images from text prompts with multiple Gemini models to balance quality, speed, and cost.
  • Edit existing images using natural language prompts and optional references to produce revised visuals.
  • Read or describe images to extract captions or insights, enabling accessibility and AI-assisted analysis.

Quick Start

Generate an image by providing a descriptive prompt to the CLI, then inspect or save the result.

Frequently Asked Questions about vertex-ai-image

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

FAQPage Schema
How do I generate images using Google Gemini from the command line?▼

Generate images by passing text prompts to the CLI, which automates Google Gemini models to produce visual content. You can balance quality, speed, and cost by selecting different models directly from your terminal.

Can I edit existing images with natural language prompts using Gemini?▼

Edit existing images by providing natural language prompts and optional references to the CLI. The Gemini models process these instructions to automatically produce revised visuals from your local files.

What file sources are supported for image generation and editing with Gemini?▼

Supported file sources for image generation and editing include local files and gs:// URIs. This allows you to process images stored locally or in Google Cloud Storage directly through the CLI.

How do I describe or analyze images to extract captions using Gemini AI?▼

Describe or analyze images to extract captions by feeding image files to the Gemini CLI. This reads visual content to generate textual insights, enabling accessibility and AI-assisted analysis.

Do I need an API key to generate and edit images with Gemini models?▼

Yes, an API key is required to generate and edit images with Gemini models. You must provide a Google Gemini API key to authenticate your CLI requests and access the generation features.

Can I adjust aspect ratios and sizes when generating images with Gemini?▼

Yes, you can adjust aspect ratios and sizes when generating images with Gemini. The CLI supports multiple models and configuration parameters, allowing you to tailor the output dimensions to your specific needs.

Related Skills

Explore More Design & Creative Skills→
zzafergokzzafergok
1

gemini-skill

Access Google Gemini models via CLI or API for reasoning and multimodal tasks.

Community
Advanced
shynlee04shynlee04

web-search

Search the web and extract content via Tavily and Exa using the inference.sh CLI.

Community
Intermediate
HuskyDannyHuskyDanny

ascii-video

Convert video, audio, images, and text into ASCII art video using Python and ffmpeg.

Community
Advanced
SignmanalSignmanal
1

stable-diffusion-image-generation

Generate images from text prompts using Stable Diffusion and HuggingFace Diffusers.

Community
Advanced