A Vulkan reimplementation of NVIDIA's DLSS 5 Neural Rendering network, bit-exact against the original.

LynnReal-Omni brings text-to-video, image-to-video, human- and hand-pose guided generation, structural control, omni-reference generation, style transfer, video editing, degraded-video restoration …

Visual Novel Character Creation Suite is a comprehensive tool for creating character sprites for visual novels. It allows you to create unique characters with a consistent appearance across all ima…

Google's open agentic orchestration runtime

Nvidia's paper Pretraining Large Language Models with NVFP4

Per-concept saliency maps for diffusion transformers, from ConceptAttention

A toolbox for skeleton-based action recognition.

🎥 Python and OpenCV-based scene cut/transition detection program & library.

Minecraft on the command line

Sloc, Cloc and Code: scc is a very fast accurate code counter with complexity calculations and COCOMO estimates written in pure Go

Stemdeck is an modern stem extraction platform for musicians,producers and hobbyists, designed to isolate vocals, drums, bass, piano and guitar for practice, transcription, remixing, and creative a…

Experimental network modules for musubi-tuner and sd-scripts

Official inference code for Krea 2

Video masking tools for ComfyUI: process a masked subject at high resolution inside a moving crop, then paste it back without jitter or visible seams

Minecraft AI with LLMs+Mineflayer

Fast RIFE with full batching and working ensemble in fp16/32 for ComfyUI

A revival of a 20th century interwar typeface.

Convert Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF to clean Markdown. Built in Rust, with Node.js and Python bindings.

Extensions for musubi tuner

Utility scripts to quantize models in optimal ComfyUI formata.

Tiny AutoEncoder for Hunyuan Video (and other video models)

Lightweight FirstBlockCache acceleration node for native ComfyUI MiniMax H3

ComfyUI custom nodes that use the MiniMax H3 video model to generate single-frame (still image) output.

ComfyUI custom nodes for OpenMOSS's MOSS-Audio audio-understanding models — speech transcription, music/mood analysis, and general audio captioning/QA in one model

An open-source model for understanding speech, environmental sounds, and music through captioning, question answering, and reasoning

Spatio-Temporal Guidance (STG) and per-modality CFG/guidance nodes for LTX-2 / LTX-2.3 in ComfyUI