bian-hengwei

Latte

Latte: Latent Diffusion Transformer for Video Generation.

stablediffusion

High-Resolution Image Synthesis with Latent Diffusion Models

ControlNet

Let us control diffusion models!

flash-attention

Fast and memory-efficient exact attention

aitom

AI for tomography

VideoMamba

[ECCV2024] VideoMamba: State Space Model for Efficient Video Understanding

XCube

[CVPR 2024 Highlight] XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies

GaussianCity

The official implementation of "GaussianCity: Generative Gaussian Splatting for Unbounded 3D City Generation". (Xie et al., arXiv 2406.06526)

DiT

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

mamba

Mamba SSM architecture

HowToCook

程序员在家做饭方法指南。Programmer's guide about how to cook at home (Simplified Chinese only).

GrootVL

[NeurIPS2024 Spotlight] The official implementation of GrootVL: Tree Topology is All You Need in State Space Model

Awesome-Evaluation-of-Visual-Generation

A list of works on evaluation of visual generation models, including evaluation metrics, models, and systems

Calib3D

Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understanding

torchsparse

[MICRO'23, MLSys'22] TorchSparse: Efficient Training and Inference Framework for Sparse Convolution on GPUs.

LMM

Large Motion Model for Unified Multi-Modal Motion Generation

FeatUp

Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024

guided-diffusion

improved-diffusion

Release for Improved Denoising Diffusion Probabilistic Models

neuralight

Neural Light Simulator for Camera-Light Calibration (a part of DarkGS project, see link below)

diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.

threefiner

An interface for text-guided mesh refinement.

GPTEval3D

[ CVPR 2024 ] Implementation for "GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generation"

InternEvo

InternEvo is an open-sourced lightweight training framework aims to support model pre-training without the need for extensive dependencies.

OpenLRM

An open-source impl. of Large Reconstruction Models

opencompass

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

xtuner

An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)

lmdeploy

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

InternLM-Math

State-of-the-art bilingual open-sourced Math reasoning LLMs.

3DTopia

Text-to-3D Generation within 5 Minutes