vrgamegirl19/comfyui-vrgamedevgirl

Custom ComfyUI nodes for film grain, color matching, and video enhancement.

What it solves

This project provides a comprehensive suite of custom nodes for ComfyUI designed to streamline the production of AI-generated video, music videos, and storyboards. It transforms ComfyUI from a simple node-based generator into a structured production workspace, solving the problem of fragmented workflows when planning, generating, and assembling complex video projects.

How it works

The core of the project is the AI Video Builder, a specialized UI that allows users to build projects based on audio, lyrics, or SRT files. It integrates planning tools like a Storyboard Builder and Reference Builder to maintain visual consistency. The system supports various video engines (such as LTX 2.3 and MiniMax H3) and provides tools for image-to-video, text-to-video, and frame-sequencing for continuity. Additionally, it includes specialized nodes for face repair, video enhancement, and LoRA training for characters and styles.

Who it’s for

This is aimed at AI artists, music video creators, and storyboard artists who use ComfyUI and want a professional, production-oriented approach to AI video creation rather than generating isolated clips.

Highlights

  • AI Video Builder: A scene-by-scene production workspace with a visual timeline and beat markers for audio-synced video.
  • Face and Video Enhancement: Dedicated tools for detecting, tracking, and repairing faces or enhancing full video clips.
  • LoRA Training Suite: Tools for creating captioned datasets and training video/audio LoRAs.
  • Integrated Audio Tools: Voice cloning (VoxCPM2), TTS, and audio splitting/timing utilities.
  • Workflow Automation: Built-in LLM prompt tools and batch-processing utilities for structured generation.

Related

  • Project
    Lightricks/ComfyUI-LTXVideo

    A collection of custom ComfyUI nodes and workflows that extend the LTX-2 video generation model with advanced control, HDR output, AI dubbing, and generative upscaling.

  • Project
    WhatDreamsCost/WhatDreamsCost-ComfyUI

    WhatDreamsCost‑ComfyUI is a collection of custom ComfyUI nodes that add video‑ and audio‑editing capabilities (timeline editor, load/trim nodes, IC‑LoRA support, audio in‑painting, etc.) for AI‑generated media workflows.

  • Project
    pixaroma/ComfyUI-Pixaroma

    ComfyUI‑Pixaroma is a genuine open‑source extension for the ComfyUI diffusion‑workflow editor. It adds a large collection of ready‑made nodes—image loading/resizing, visual crop & paint tools, 3‑D scene builder, audio‑reactive video, LoRA stacking, text utilities, XY‑plot comparison, and workflow helpers—plus built‑in help panels and example workflows. The goal is to make everyday AI‑image generation tasks more visual and user‑friendly, letting artists and developers build, preview, and tweak pipelines without leaving ComfyUI.

  • Project
    shootthesound/comfyUI-Realtime-Lora

    A comprehensive ComfyUI toolkit for training, analyzing, and selectively loading LoRAs across multiple model architectures, featuring granular block-level and sub-component control.

  • 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.