Starred repositories
[ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing
MatlowAI's MiniMax-H3 ComfyUI nodes: Contact-Sheet diffusion + Motion Lab (test-time de-roping of fast motion)
Neural latent upscaler for Minimax H3 (24ch). Bypasses costly 5B-param VAE decode/encode. Upscale low-res latents directly, then refine. Accelerates high-res video gen, outperforms naive interp.
OmniVBench & Omni-R2V Dataset: A Benchmark and Large-Scale Dataset for Omni Reference-to-Video Generation
🚧 Under construction — no-training RefMod reference adapters for MiniMax H3 (compress reference images/videos into tiny latents, no training needed).
Multimodal RL training framework for diffusion & omni models
Windows desktop workspace for local LoRA training. Integrates kohya, musubi-tuner, AI Toolkit and Fizgig with guided setup, dataset tools, sample comparison and local MCP access.
Making it easier to work with slang in python
Implementation of Peter Shirley's Ray Tracing In One Weekend book using Vulkan and NVIDIA's RTX extension.
Repository containing common 3D test models in original format with original source if known and obj mesh
dgaf 的 《DirectX 12 快速教程》配套代码 (A Sample of dgaf's DirectX 12 Quick Beginner Tutorial)
Open Data Platform for analysts, quants and AI agents.
A Curated List of Awesome Works in World Modeling, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts Interested in World Modeling.
Tiny but powerful single file wavefront obj loader
🎨 ML Visuals contains figures and templates which you can reuse and customize to improve your scientific writing.
An open survey on 3D Gaussian Splatting compression methods
Main Web Site (Online Books)
Superpoint Gaussians Splatting for Real-Time High-Fidelity Monocular Dynamic Scene Reconstruction