Gemini Image Studio
@udhaykumarbala
MCP server for AI image generation and editing with Google Gemini (NanoBanana). Features structured JSON editing — decompose any image into a blueprint, then edit specific components with dot-notation paths. 5 tools, 10 built-in presets for ads, web, and social media.
Overview
What is Gemini Image Studio?
Gemini Image Studio is an MCP server that integrates with Google's Gemini to generate, edit, and decompose images using text or JSON prompts. It offers preset support and a structured JSON editing pipeline for precise, targeted changes. It is designed for developers and content creators who need programmatic control over image generation and modification.
How to use Gemini Image Studio?
—
Key features of Gemini Image Studio
- generate_image — Create images from text or JSON prompts with preset support
- decompose_image — Analyze images into structured JSON blueprints
- edit_image — Edit via JSON dot-notation paths or natural language
- get_presets — 10 built-in presets for common formats (Facebook ads, Instagram stories, hero images, OG images, YouTube thumbnails, etc.)
- list_generated — Browse generated images with metadata and edit history
Use cases of Gemini Image Studio
- Generate social media assets (ads, stories, thumbnails) using presets
- Decompose an existing image into a modifiable JSON blueprint
- Edit specific image fields (e.g.,
subject[0].hair.color) without affecting the rest of the image - Browse previously generated images and their edit history for reuse or iteration
FAQ from Gemini Image Studio
What makes Gemini Image Studio different from other image generation tools?
It uses a structured JSON editing pipeline: generate → decompose → edit specific fields → regenerate. This allows precise changes without affecting the rest of the image.
What presets are available?
The server includes 10 built-in presets for common formats such as Facebook ads, Instagram stories, hero images, OG images, and YouTube thumbnails.
Can I edit images using natural language?
Yes, the edit_image tool supports both JSON dot-notation paths and natural language instructions for editing.
