Which AI image providers does Artifex support?

Artifex currently supports Google's Antigravity (utilizing the Gemini 3 Pro Image model) and OpenAI's DALL-E 3, allowing users to switch between them easily.

Does Artifex offer consistent character generation?

Yes, for users of the Antigravity provider, Artifex provides session-based character consistency, which helps maintain the look of characters across multiple generated images.

Is Artifex an official tool from Google or OpenAI?

No, Artifex is an independent, community-developed open-source project. It is not affiliated with, endorsed by, or supported by Google or OpenAI.

Artifex MCP is an independent Model Context Protocol (MCP) server designed for generating and editing AI images. It offers a unified interface to interact with multiple AI image providers.

Can I edit existing images with Artifex?

Yes, Artifex supports image editing with text instructions, though this feature is currently available only when using the Antigravity (Gemini 3 Pro Image) provider.

Artifex

Name: Artifex
Author: jkalasas

•

Provides a vendor-agnostic Model Context Protocol (MCP) server for generating and editing AI images across multiple providers like Google's Antigravity and OpenAI's DALL-E 3.

概要

Artifex is an independent, community-developed Model Context Protocol (MCP) server designed for AI image generation. It acts as a vendor-agnostic interface, allowing users to generate and edit images using various providers, currently supporting Google's Gemini 3 Pro Image (Antigravity) and OpenAI's DALL-E 3. This flexibility enables switching between models with a simple parameter, supporting diverse creative tasks from text-to-image generation to advanced image editing, character consistency, and multiple output variations, making it a powerful tool for integrating AI imaging capabilities into MCP clients.

主な機能

Session-based Character Consistency (Antigravity only)
Image Editing (Antigravity only)
Text-to-Image Generation
Multi-Provider Support (Antigravity/Gemini 3 Pro Image, OpenAI/DALL-E 3)
7 GitHub stars
Multiple Image Outputs (up to 4, Antigravity only)

ユースケース

Integrating AI image generation into MCP client configurations (e.g., Claude Desktop, OpenCode)
Generating diverse AI images from text prompts using various models
Editing existing images with AI instructions and maintaining character consistency