Awesome GitHub RepositoriesComfyUI Custom Node Suites

I've made everythign less reliant on torch.compile for VRAM efficiency, so things should work better even without it. Also figured workaround for some issues when using compile that made first run use drastically more VRAM, issue I battled with myself a lot.

ComfyUIIPAdapterplus ist eine knotenbasierte Erweiterung für ComfyUI, die IPAdapter-Modelle implementiert, um die Bildgenerierung unter Verwendung von Referenzbildern zu steuern. Sie fungiert als Bild-Prompting-Tool und Stable-Diffusion-Bildadapter, der es ermöglicht, Referenzdateien als visuelle Prompts zur Steuerung von Stil, Komposition und Subjektidentität zu verwenden. Das Projekt bietet spezialisierte Funktionen zur Wahrung der Gesichtsidentität und hochauflösender Merkmale über generierte Porträts hinweg. Es ermöglicht die Übertragung visueller Eigenschaften und künstlerischer Stile von Referenzbildern sowie die Extraktion räumlicher Layouts, um die Anordnung von Objekten in neuen Generationen zu steuern. Die Erweiterung deckt breite Funktionsbereiche ab, einschließlich KI-Bildkonditionierung, konsistenter Charaktergenerierung und Bildkompositionskontrolle.

Dieses Projekt ist eine ComfyUI-ControlNet-Preprocessor-Suite und ein Computer-Vision-Analyse-Toolkit. Es fungiert als Stable-Diffusion-Bild-Preprocessor, der strukturelle Hinweise aus Bildern extrahiert, um latente Diffusions-Workflows zu steuern. Das System bietet spezialisierte Modelle für die menschliche Pose-Schätzung, einschließlich skelettaler Keypoints und Gesichts-Meshes, sowie 3D-Szenen-Mapping durch Tiefen- und Oberflächennormalenschätzung. Es enthält zudem Tools für KI-Videobewegungssteuerung mittels optischer Flussanalyse. Die breitere Funktionspalette deckt die strukturelle Bildanalyse ab – wie Line-Art, Kantenerkennung und semantische Segmentierung – sowie Luminanz-Isolierung und die Generierung von Farb- und Stilhinweisen. Diese Prozesse werden durch hardwarebeschleunigte Runtimes und Model-Checkpoint-Caching unterstützt, um die Inferenz-Latenz zu reduzieren.

Nunchaku is a 4-bit model quantization library and diffusion model inference engine designed to run large-scale neural networks on consumer GPUs. It functions as a GPU-accelerated optimizer that reduces VRAM usage and increases inference speed through weight compression and memory management. The project utilizes low-rank weight decomposition and SVD weight quantization to compress models to four-bit precision while maintaining visual fidelity. It employs kernel-level operator fusion to minimize data movement and hardware-aware precision mapping to adjust numerical precision based on the unde

ComfyUI-LTXVideo is a generative framework and ComfyUI custom node extension for synthesizing high-fidelity video. It utilizes a latent diffusion and transformer-based system to create cinematic clips from text, image, and audio inputs, providing a modular interface for precise control over subject behavior and temporal consistency. The tool distinguishes itself with production-grade capabilities, including the generation of High Dynamic Range video in linear formats such as ARRI LogC3. It supports multimodal synchronization for audio-driven animation and lip-syncing, and allows for the creat

ComfyUI-3D-Pack is a suite of custom nodes for ComfyUI that enables 3D asset generation and rendering within a node-based workflow. It provides a set of tools for reconstructing textured three-dimensional meshes and volumetric scenes from single images, multi-view images, or text prompts. The system includes a Gaussian splatting generator for creating high-fidelity volumetric 3D scene representations and a multi-view image generator to produce consistent image sets for reconstruction. It also features a single image 3D mesh tool to build geometry from a single 2D source. The toolset covers 3

ComfyUI-GGUF is a memory optimizer and model loader for ComfyUI that enables the execution of large transformer-based generative models using quantized weights. It provides a system for loading GGUF formatted weights within a node-based diffusion interface to reduce GPU memory consumption. The project includes a quantization tool for converting standard model checkpoints into compressed binary formats and a tensor fixer to restore missing keys and correct architectures in binary model files. These utilities ensure that compressed models remain functional during inference on hardware with limi

ComfyUI-nunchaku is a 4-bit diffusion inference engine and a set of nodes for running low-precision quantized diffusion models within ComfyUI visual workflows. It provides a backend that reduces memory overhead and increases generation speed for transformer models. The project includes specialized tools for identity-preserving generation and an image-to-image guidance toolkit that uses depth maps and reference images. It also features a multimodal visual question answering implementation and a utility for merging multiple quantized model files into single unified files. The engine covers a b

rgthree-comfy is a collection of custom nodes and interface enhancements designed to automate and organize generative AI workflows within ComfyUI. It provides a specialized toolset for node-based automation, dynamic data routing, and graph management. The project distinguishes itself through a dynamic data router and workflow management tools that enable bulk muting, bypassing, and navigation of complex node graphs via bookmarks and visual labels. It also includes logic and math nodes for evaluating expressions and image processing utilities for side-by-side comparisons and precise cropping.

ComfyUI-Easy-Use is a custom node suite and workflow optimizer designed to simplify Stable Diffusion generation pipelines. It provides a set of integrated tools to reduce visual clutter and streamline the process of creating images from text and existing image references. The project distinguishes itself through a pipeline manager that consolidates models, conditioning, and latents into unified data pipes, eliminating complex wiring in the node graph. It also introduces a logical operator set that enables conditional if-else branching and for-loop structures directly within the visual program

Matchering is an audio mastering tool and Python library designed to match the frequency balance and loudness of a target track to a specific reference track. It functions as a reference-based mastering system that aligns a target signal's spectral envelope, RMS, and peak amplitude with those of a chosen reference file. The project utilizes a multi-stage processing pipeline featuring an FFT spectral matching engine to adjust frequency response. It ensures output quality through the use of a brickwall limiter to prevent signal clipping while preserving the original waveform shape. The tool pr