AHEKOT/ComfyUI_VNCCS_Utils

A collection of utility nodes from the VNCCS project that are useful not only for the project's primary goals but also for everyday ComfyUI workflows.

What it solves

This project provides a suite of advanced utility nodes for ComfyUI that bridge the gap between 2D image generation and 3D asset creation, posing, and complex canvas-based editing. It eliminates the need to switch between multiple external software tools for 3D Gaussian Splatting, character posing, and infinite-canvas image composition within a single generative AI workflow.

How it works

The toolkit consists of several specialized workspaces integrated as ComfyUI nodes:

  • VNCCS 3D Factory: Implements a local TripoSplat pipeline to convert images into 3D Gaussian models. It includes a persistent scene manager and a SparkJS viewport for rendering, transforming, and exporting Gaussian PLY assets.
  • VNCCS UniCanvas: Provides an infinite-canvas environment for layer-based image generation and editing, allowing users to generate, inpaint, and outpaint across a freeform workspace using SAM-powered object selection.
  • VNCCS Pose Studio: A 3D mannequin environment for creating pose and lighting references. It supports bone manipulation, keyframe animation, Mixamo FBX imports, and dynamic body shape adjustments.
  • Supporting Utilities: Includes a visual camera control widget for multi-angle LoRAs, a QWEN-powered detailer for vision-guided region enhancement, and a model manager for downloading and selecting assets from HuggingFace and Civitai.

Who it’s for

Digital artists, 3D designers, and AI generative artists using ComfyUI who need professional-grade control over 3D assets, character posing, and complex image composition without leaving their node-based workflow.

Highlights

  • Integrated 3D Gaussian Workspace: Local TripoSplat pipeline with a live viewport for managing and exporting 3D Gaussian PLY objects.
  • Infinite Canvas Editing: Layer-based composition and generation anywhere on a freeform canvas.
  • Professional Posing Tools: Interactive 3D mannequin with animation timelines, Mixamo support, and advanced environment lighting.
  • Vision-Guided Detailing: Smart cropping and enhancement of specific regions using QWEN-Image-Edit.
  • Unified Model Management: Visual card-based UI for managing and updating models from remote repositories.

Related

  • Project
    filliptm/ComfyUI_Fill-Nodes

    A versatile collection of custom nodes for ComfyUI that adds advanced image processing, VFX, file handling, and integrations with external AI APIs like GPT and Gemini.

  • 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
    chflame163/ComfyUI_LayerStyle

    A set of ComfyUI nodes that bring Photoshop-like layer and mask compositing functionality to the platform, reducing the need for external editing software.

  • Project
    Acly/comfyui-tooling-nodes

    A set of ComfyUI custom nodes and API extensions that enable the use of ComfyUI as a backend for external tools, featuring optimized image transfer, regional prompting, and model inspection.

  • Project
    YanWenKun/ComfyUI-Windows-Portable

    A ready‑to‑run Windows package that bundles ComfyUI (a node‑based UI for Stable Diffusion) with 40+ custom nodes and 300+ pre‑compiled Python packages, letting users launch AI image/video generation instantly on an NVIDIA GPU.