Official Torch/CUDA Implementation of Faithful Contouring

Spelling, grammar and style checking on LaTeX documents

一个基于nano banana pro🍌的原生AI PPT生成应用，迈向真正的＂Vibe PPT＂; 支持上传任意模板图片；上传任意素材&智能解析；一句话/大纲/页面描述自动生成PPT；口头修改指定区域、一键导出 - An AI-native PPT generator based on nano banana pro🍌

Qwen-Image-Layered: Layered Decomposition for Inherent Editablity

Code repository for the paper "Inferring Compositional 4D Scenes without Ever Seeing One".

HY-World 1.5: A Systematic Framework for Interactive World Modeling with Real-Time Latency and Geometric Consistency

RealSee3D: A multi-view RGB-D dataset combining real-world captures and procedurally generated scenes, with extensible annotations for diverse 3D vision research.

Native and Compact Structured Latents for 3D Generation

Official inference repo for FLUX.1 models

🤱🏻 Turn any webpage into a desktop app with one command.

"MoCA: Mixture-of-Components Attention for Scalable Compositional 3D Generation"

[CVPR 2025 Highlight] MATCHA: Towards Matching Anything

Unleashing Vecset Diffusion Model for Fast Shape Generation / within 1 Second (ICCV'25 Highlight)

An AI agent that automates the creation of CVPR/NeurIPS standard academic diagrams. Implements a strict "Logic (Architect) -> Vision (Renderer)" workflow to transform paper abstracts into high-fide…

♊ 50+ selected Gemini prompts with images, multilingual support, and instant gallery preview. Open-source prompt engineering library

令人惊艳的定格动画生成器，基于单张图片创建,基于每个姿势使用 Gemini Nano Banana 生成动画帧,合成gif

cuTile is a programming model for writing parallel kernels for NVIDIA GPUs

[NeurIPS 2025 Spotlight] Official implementation of the SIU3R: Simultaneous Scene Understanding and 3D Reconstruction Beyond Feature Alignment

LATTICE: Democratize High-Fidelity 3D Generation at Scale

TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models

🌍 WorldGen - Generate Any 3D Scene in Seconds

Code for "FlashWorld: High-quality 3D Scene Generation within Seconds"

[arXiv] SwiftVGGT: A Scalable Visual Geometry Grounded Transformer for Large-Scale Scenes

[arXiv'25] AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backend

Code for "RUBIK:A Structured Benchmark for Image Matching across Geometric Challenges", CVPR 2025

🐹 Deep clean and optimize your Mac.

The power of Claude Code / GeminiCLI / CodexCLI + [Gemini / OpenAI / OpenRouter / Azure / Grok / Ollama / Custom Model / All Of The Above] working as one.

🪐 Objaverse-XL is a Universe of 10M+ 3D Objects. Contains API Scripts for Downloading and Processing!