Pixelle is an AIGC solution that converts ComfyUI workflows into MCP (Model Context Protocol) tools, enabling multimodal AI content generation powered by LLMs with zero code.

What types of content does Pixelle support?

Pixelle supports full-modal AI content generation, including text, image, sound/speech, and video (TISV).

How does Pixelle simplify AI tool development?

It enables zero-code development by allowing users to define and dynamically add new MCP tools through seamless conversion of existing ComfyUI workflows.

What deployment options are available for Pixelle?

Pixelle offers flexible deployment, allowing you to run it as a standalone server, a standalone client, or a combined server-client setup based on your needs.

Can Pixelle integrate with other AI clients or agents?

Yes, its robust MCP Server integrates with any MCP-compatible client, such as Cursor or Claude Desktop, providing versatile AI solutions.

Pixelle

Name: Pixelle
Author: AIDC-AI

byAIDC-AI

•

935

•

開発者ツール

データサイエンスとML

API開発

Converts ComfyUI workflows into MCP tools to enable multimodal AI-generated content solutions powered by LLMs.

Pixelle is an open-source, omnimodal agent framework that seamlessly integrates ComfyUI with Large Language Models (LLMs) via the Model Context Protocol (MCP). It allows users to convert complex ComfyUI workflows into callable MCP tools with zero code, empowering LLMs to perform a wide range of AIGC tasks across text, image, sound/speech, and video. Built on the extensible ComfyUI ecosystem, Pixelle provides a flexible and unified solution for developing, deploying, and utilizing multimodal AI generation capabilities through a powerful client-server architecture.

主な機能

01Supports full-modal (Text, Image, Sound/Speech, Video) conversion and generation.

02Built on ComfyUI, inheriting its entire open ecosystem capabilities.

03Enables zero-code development and dynamic addition of new MCP tools from ComfyUI workflows.

04Provides a robust MCP Server for integration with any MCP client (e.g., Cursor, Claude Desktop).

05Offers flexible deployment options, including standalone server, standalone client, or combined.

0695 GitHub stars

ユースケース

01Integrating advanced AI generation capabilities into existing MCP-compatible applications and platforms.

02Transforming custom ComfyUI workflows into easily callable AI tools for LLMs.

03Building multimodal AI agents capable of generating and converting various content types.