gemini-image-generator

Convert prompts and images into Gemini image generation API calls.

1|Updated Dec 25, 2025
One-click install
npx skills add https://github.com/feed-mob/agent-skills --skill gemini-image-generator-feed-mob
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gemini-image-generator
Source: https://github.com/feed-mob/agent-skills/tree/main/skills/gemini-image-generator
Command: npx skills add https://github.com/feed-mob/agent-skills --skill gemini-image-generator-feed-mob

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai, pillow, requests, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates Gemini Nano Banana image generation, editing, and logo overlay workflows by converting user prompts into API calls through bundled Python scripts. It helps you quickly produce consistent visuals, apply edits, and add branding without manual repetitive steps.

Core Features & Use Cases

  • Automated generation: Create images from prompts with configurable aspect ratios and resolutions (defaults: 9:16, 1 image, Flash model; Pro adds higher quality options).
  • Edit / image-to-image: Transform existing images or apply edits using prompts and optional references.
  • Logo overlays: Place logos on base images with consistent lighting and perspective using Pro features.
  • Reference support: Use multiple references to guide fidelity; Pro mode enables more references and larger sizes.
  • Use Case: Rapidly generate marketing visuals from a brand prompt, then batch edit and overlay logos for marketing campaigns.

Quick Start

Generate a 2K, 16:9 cinematic still of a neon city at night with the prompt: "neon city at night, rainy, cyberpunk".

Frequently Asked Questions about gemini-image-generator

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

FAQPage Schema
How do I generate images using Gemini prompts?

Image generation with Gemini converts text prompts into visuals by invoking the Google GenAI API with configurable aspect ratios and resolutions. The Skill accepts prompts, selects between Flash (fast) and Pro (higher quality) models, and outputs timestamped PNG files to a dedicated directory.

Can I edit existing images and apply transformations with Gemini?

Yes, image-to-image editing transforms existing images by loading them from URLs or local paths, combining them with text prompts and optional reference images, then invoking Gemini's edit API. Pro mode enables larger reference sizes and more references for guided fidelity.

How do I add logo overlays to images with consistent lighting and perspective?

Logo overlay automation places logos on base images while maintaining consistent lighting and perspective using Pro-only features. The Skill loads base and logo images, combines them with a prompt describing placement intent, then generates the composite output.

What aspect ratios and resolutions does Gemini image generation support?

The Skill supports configurable aspect ratios and resolutions with validation built in. Defaults are 9:16 and 1 image using the Flash model; Pro model unlocks higher quality resolutions and additional generation options for marketing and creative workflows.

Does this work with images from URLs and local file paths?

Yes, the Skill loads images from both URLs and local paths, validates input formats via Pillow, and passes them to Gemini's API for editing or reference-guided generation. Outputs save as timestamped PNGs in the outputs directory.

What are the limitations when using multiple reference images for guidance?

Flash model supports fewer references and smaller image sizes; Pro mode enables multiple references and larger sizes for more precise fidelity guidance. Reference count and dimensions are validated before API invocation to ensure compatibility.