skills.rest
yzavyas
yzavyasCOMMUNITY
Explore all skills by this author →
GitHub

visual-creation

Generate AI visuals from natural language prompts using Gemini/Imagen APIs.

7|3|Updated Dec 1, 2025
Search Tags:#image-generation#generate#prompt-engineering#video-generation#AI-art#Gemini-Imagen
One-click install
npx skills add https://github.com/yzavyas/claude-1337 --skill visual-creation
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: visual-creation
Source: https://github.com/yzavyas/claude-1337/tree/main/plugins/visuals-1337/skills/visual-creation
Command: npx skills add https://github.com/yzavyas/claude-1337 --skill visual-creation

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-generativeai, Pillow, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill enables rapid creation of AI-driven artwork and visual assets from natural language prompts, reducing manual design time and enabling quick concept exploration.

Core Features & Use Cases

  • Image generation from text prompts using Gemini/Imagen 3.0.
  • Optional style hints to guide color, mood, and composition.
  • Basic video generation workflows or frame-based visuals for concept previews.
  • Suitable for artwork creation, illustrations, storyboards, and social visuals.

Quick Start

Launch the gemini-image.py script with your prompt to generate a visual. Example: python scripts/gemini-image.py "arcane sigil over a neon city" --output output.png --style mystical. Ensure you have Google API Key configured (GOOGLE_API_KEY or --api-key).

Frequently Asked Questions about visual-creation

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

FAQPage Schema
How do I generate AI images from text prompts using Gemini?▼

Generate AI images from text prompts by running the gemini-image.py script with your natural language query. You can pass style hints to influence color, mood, and composition, outputting the artwork to a specified file path.

Can I use Imagen 3.0 for concept previews and storyboards?▼

Imagen 3.0 supports concept previews and storyboards by generating frame-based visuals from text prompts. It enables rapid exploration of artwork, illustrations, and social visuals for marketing and storytelling.

Do I need a Google API key to use Gemini for image generation?▼

A valid Google API key is required to use Gemini for image generation. You must configure it as an environment variable or pass it via command line, alongside installing the google-generativeai and Pillow dependencies.

What is the best way to apply style hints to AI-generated artwork?▼

Apply style hints to AI-generated artwork by passing the style parameter when running the image generation script. This guides the API to influence the color, mood, and overall composition of the resulting visual asset.

Does this visual creation method work for marketing design and social visuals?▼

This visual creation method works for marketing design and social visuals by reducing manual design time. It allows quick concept exploration and generates tailored illustrations directly from natural language prompts.

Related Skills

Explore More Design & Creative Skills→
cdeistopenedcdeistopened
24

image-prompt-generator

Generate custom AI images with Google's Gemini API.

Community
Intermediate
seanrobertwrightseanrobertwright
2

video-processor

Transcribe videos, generate chapters, thumbnails, and social media images.

Community
Intermediate
ArnavPuriArnavPuri
3

image-generation

Generate and edit images using the Gemini 3.1 Flash Image Preview model.

Community
Intermediate
danfrdndanfrdn

gemini-imagegen

Generate and edit images using the Gemini API with text prompts.

Community
Intermediate