skills.rest
zephyrwang6
zephyrwang6COMMUNITY
Explore all skills by this author →
GitHub

gemini-image

Generate images from text prompts and reference image URLs via API calls.

14|4|Updated Mar 31, 2026
Search Tags:#prompt engineering#image generation#visual design#ai art#text to image#image to image
One-click install
npx skills add https://github.com/zephyrwang6/allSkills --skill gemini-image-zephyrwang6
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gemini-image
Source: https://github.com/zephyrwang6/allSkills/tree/main/gemini-image
Command: npx skills add https://github.com/zephyrwang6/allSkills --skill gemini-image-zephyrwang6

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps you create images from plain language prompts or reference images without manual illustration work, making visual creation faster and more accessible.

Core Features & Use Cases

  • Text to Image: Turn a written concept into a generated picture, such as a mascot, product mockup, or scene illustration.
  • Image to Image: Use an existing image as a visual reference and generate a new version with a different style or composition.
  • Multi-Image Reference: Combine multiple image URLs and a prompt to guide a more specific creative result.

Quick Start

Ask the skill to generate an image from your idea, such as creating a cute orange cat illustration in a bright, friendly style.

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 prompts and reference images?▼

Image to image generation uses an existing image URL as a visual reference to produce a new version. You provide the reference image and a text prompt to guide style transfer or composition changes, receiving a new generated image URL.

Can I use multiple image URLs to guide a specific creative result?▼

Multi-image reference workflows combine multiple image URLs and a text prompt to guide highly specific creative results. This allows you to merge visual elements from several references into a single generated illustration or concept art piece.

Does text to image generation work for concept art and style transfer tasks?▼

Text to image generation supports concept art and style transfer tasks by converting plain language prompts into visual illustrations. This automates manual illustration work for creating mascots, product mockups, or scene illustrations.

What do I need to provide for prompt assembly and image URL handling?▼

Prompt assembly and image URL handling require your plain text concept and any reference image URLs. You do not need manual illustration skills; the API calls process these inputs to return the final generated image URL output.

Related Skills

Explore More Design & Creative Skills→
agentspace-soagentspace-so
31

gpt-image-2

Generate and edit brand-safe images with GPT Image 2 on the RunComfy Model API.

Official
Intermediate
pinion05pinion05
3

youtube-transcript

Extract YouTube transcripts and metadata into Markdown for Obsidian.

Community
Advanced
vuminhieuvuminhieu

ai-artist

Craft structured prompts for AI text and image generation tasks.

Community
Advanced
xiaxianlinxiaxianlin
1

gpt-image-gen

Generate images from text prompts and apply style transfers via the APIMart GPT-Image-2 API.

Community
Intermediate