AllenPeng0209

Deep-Live-Cam

real time face swap and one-click video deepfake with only a single image

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

LLM101n

LLM101n: Let's build a Storyteller

flux

Official inference repo for FLUX.1 models

flash-attention

Fast and memory-efficient exact attention

nerfstudio

A collaboration friendly studio for NeRFs

Unique3D

Official implementation of Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image

MambaOut

MambaOut: Do We Really Need Mamba for Vision?

VILA

VILA - a multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and laptops)

nano-llama31

nanoGPT style version of Llama 3.1

openvla

OpenVLA: An open-source vision-language-action model for robotic manipulation.

ovsam

[ECCV 2024] The official code of paper "Open-Vocabulary SAM".

flowmap

Code for "FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descent" by Cameron Smith*, David Charatan*, Ayush Tewari, and Vincent Sitzmann

GaussianPro

[ICML2024] Official code for GaussianPro: 3D Gaussian Splatting with Progressive Propagation

DriveAGI

[CVPR 2024 Highlight] GenAD: Generalized Predictive Model for Autonomous Driving & Foundation Models in Autonomous System

diffusion-forcing

code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"

ComfyFlowApp

From comfyui workflow to web app, in seconds

1d-tokenizer

This repo contains the code for our paper An Image is Worth 32 Tokens for Reconstruction and Generation

S3Gaussian

Official Implementation of Self-Supervised Street Gaussians for Autonomous Driving

l4casadi

Use PyTorch Models with CasADi for data-driven optimization or learning-based optimal control. Supports Acados.

street-gaussians-ns

Unofficial implementation of "Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting", ECCV2024.

autoregressive-diffusion-pytorch

Implementation of Autoregressive Diffusion in Pytorch

fast-gaussian-rasterization

A geometry-shader-based, global CUDA sorted high-performance 3D Gaussian Splatting rasterizer. Can achieve a 5-10x speedup in rendering compared to the vanialla diff-gaussian-rasterization.

General-World-Models-Survey

TokenPacker

The code for "TokenPacker: Efficient Visual Projector for Multimodal LLM".

titok-pytorch

Implementation of TiTok, proposed by Bytedance in "An Image is Worth 32 Tokens for Reconstruction and Generation"

OccSora

OccSora: 4D Occupancy Generation Models as World Simulators for Autonomous Driving

CVT-Occ

CVT-Occ: Cost Volume Temporal Fusion for 3D Occupancy Prediction

ComfyUI-Llama-3-2

Using Llama-3.2 in ComfyUI

S3Gaussian

Project Page for S3Gaussian