VelornLabs/velorn

AI-native video editing built around real creative timelines, generative workflows, and local agent control.

What it solves

Velorn is an open-source desktop video editor and AI video workstation designed to bridge the gap between AI generation and final production. It solves the problem of fragmented workflows by combining planning, asset generation, timeline editing, captions, and export into a single project-based application.

How it works

Velorn acts as a production layer around ComfyUI. While it provides built-in local and cloud workflows, it integrates deeply with a local ComfyUI server to run image, video, and audio generation. Users can import custom ComfyUI API workflow JSONs or use the "Velorn Bridge" to send graphs directly from ComfyUI to the app. For automation, it includes a local MCP (Model Context Protocol) server with over 100 tools, allowing AI agents (like Claude or Cursor) to inspect projects, edit timelines, and queue generation work.

Who it’s for

It is designed for creators making music videos, UGC-style social ads, business advertisements, and experimental short films who want to integrate AI-generated assets into a professional editing timeline.

Highlights

  • Integrated Timeline Editor: Multi-track video/audio editing with trimming, transitions, effects, and proxy/cache tools.
  • Guided Creator Workflows: Specialized modes for music videos (with lyric timing and ASR transcription) and ad creation.
  • ComfyUI Integration: Deep support for local and cloud workflows, including a dependency checker for missing nodes and models.
  • Agentic Automation: A local MCP server that enables AI agents to perform timeline operations and manage generation workflows.
  • AI Captions: Timeline-aware transcription and styling tools for generating export-ready captions.
  • Stock Integration: Built-in Pexels search for importing photos and videos directly into projects.

Related

  • Project
    jtydhr88/ComfyTV

    A canvas-based media workbench for ComfyUI that integrates AI generation with professional-grade editing tools for image, video, audio, music, and 3D assets.

  • Project
    vrgamegirl19/comfyui-vrgamedevgirl

    A collection of ComfyUI custom nodes featuring an AI Video Builder for scene-by-scene production, video enhancement, and LoRA training for AI video and music video creation.

  • Project
    Comfy-Org/ComfyUI

    A modular, node-based AI engine for visual professionals to create complex workflows for generating images, video, audio, and 3D models with precise parameter control.

  • Project
    ddcat-ai/open-ai-canvas

    Open‑AI‑Canvas (影策) is an open‑source, self‑hosted web workbench that lets creators turn a text brief into a complete set of film‑style assets—storyboards, character/style libraries, and AI‑generated images, video and audio—through an integrated canvas, async task queue and local AI‑agent system.

  • Project
    visualbruno/3DGenStudio

    3D Gen Studio is an open‑source, AI‑driven desktop/web app that lets you build 3‑D assets end‑to‑end. It combines a Kanban board or node‑graph UI with ComfyUI workflows and external 3‑D generation APIs, offering image‑to‑mesh pipelines, auto‑UV/retopo, AI‑auto‑rigging (SkinTokens + optional Kimodo motion), LOD/optimization, and game‑ready checks—all stored locally on disk.