jtydhr88/ComfyTV

ComfyTV — the canvas-based app that truly belongs to ComfyUI.

What it solves

ComfyTV transforms ComfyUI from a standard node-based graph into a comprehensive, canvas-based media workbench. It solves the fragmented nature of AI content creation by integrating generation, editing, compositing, and exporting for images, video, audio, and 3D assets into a single, project-centric flow where results are preserved and easily iterated upon.

How it works

ComfyTV introduces a "Per-node Run" system where each stage operates independently rather than through a global queue, allowing users to update specific parts of a chain without re-running the entire workflow. It integrates directly with ComfyUI as a custom node suite, allowing users to import JSON workflows and bind them to a GUI editor. The system includes a vast library of specialized nodes (~190 stages) across multiple modalities, a built-in asset library, and an MCP server that allows AI agents to programmatically control the canvas, build nodes, and inspect results.

Who it’s for

It is designed for AI artists, video editors, and multimedia producers who use ComfyUI and want a more structured, non-destructive editing environment that combines generative AI with traditional production tools (like layer editors, piano rolls, and video FX).

Highlights

  • Multimodal Workbench: Integrated tools for image generation/editing, video compositing, audio processing, symbolic music composition, and 3D scene management.
  • Advanced Editors: Embedded in-node editors for 2D layers (with PSD support), storyboards, and piano rolls for MIDI/MusicXML.
  • Agent-Native Integration: Includes a built-in chat bot and an MCP server with 45 tools, enabling AI agents (like Claude Code) to drive the creative process.
  • Project-Centric Workflow: Maintains full history and snapshots of outputs, with deep integration for the Eagle archive app for asset management and provenance tracking.
  • Comprehensive Video Suite: Over 100 nodes covering everything from chroma keying and roto-tracking to complex FX chains and 360° footage stabilization.

Related

  • Project
    Comfy-Org/ComfyUI

    A modular, node-based AI engine for visual professionals to create images, videos, audio, and 3D models with precise control over every parameter.

  • Project
    tigerowo/infinite-canvas

    An open-source multimodal AI creative workbench that combines an infinite canvas with AI image, video, and audio generation tools to streamline visual iteration.

  • Project
    hero8152/Infinite-Canvas

    A visual, infinite canvas workspace that integrates multiple AI APIs and local ComfyUI workflows for collaborative generative AI content creation.

  • Project
    pixaroma/ComfyUI-Pixaroma

    ComfyUI‑Pixaroma adds a large set of user‑friendly nodes to the ComfyUI visual workflow engine, covering image/video/3D I/O, prompt handling, notes, logic controls, resizing, and built‑in editors. It streamlines common tasks, offers extensive documentation, and is installed via Easy‑Install or a simple Git clone.

  • Project
    suki0dayo/AI_film_studio

    A node-based visual editor that streamlines AI movie production by automating the workflow between LLMs for prompting and ComfyUI for image and video generation.