Native and Compact Structured Latents for 3D Generation

ClangQL is a tool that allow you to run SQL-like query on C/C++ Code instead of database files using the GitQL SDK

A Stellaris Galaxy Mod - One Galaxy to Rule Them All

Maple Mono: Open source monospace font with round corner, ligatures and Nerd-Font icons for IDE and terminal, fine-grained customization options. 带连字和控制台图标的圆角等宽字体，中英文宽度完美2:1，细粒度的自定义选项

Efficient Part-level 3D Object Generation via Dual Volume Packing

Official repo for paper "Sparse Representation and Construction for High-Resolution 3D Shapes Modeling".

OmniGen2: Exploration to Advanced Multimodal Generation. https://arxiv.org/abs/2506.18871

The official code repository for LeVo: High-Quality Song Generation with Multi-Preference Alignment

Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)

Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.

Cross-platform game engine in Rust.

OOMOL Studio's workflow engine, implemented in Rust.

A fast AI Video Generator for the GPU Poor. Supports Wan 2.1/2.2, Qwen Image, Hunyuan Video, LTX Video and Flux.

Your Creative Copilot for Video Editing

An official implementation of EvoSearch: Scaling Image and Video Generation via Test-Time Evolutionary Search

MAGI-1: Autoregressive Video Generation at Scale

A Python-Script Based Generative AI platform

FramePack with existing video input.

cosyvoice 混合多方修改版的可用版

online video editor built with nextjs, remotion and ffmpeg (web assembly port) for render.

超好用的截图工具

Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation".

一个工具网站，提供各种实用的在线工具，助您提高工作效率。无需安装，随时随地使用

所有小初高、大学PDF教材。

2025新春版：一个近乎完美的Konva手写板诞生记

image management that have user friendly interaction and ai tag Using wd1.4 tagger.

The UI design language and React library for Conversational UI

[NeurIPS 2025] Image editing is worth a single LoRA! 0.1% training data for fantastic image editing! Surpasses GPT-4o in ID persistence~ MoE ckpt released! Only 4GB VRAM is enough to run!