wookiekim

Seungwook Kim's starred repositories

llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Language:Jupyter NotebookApache-2.035255 366 65

OpenVoice

Instant voice cloning by MyShell.

Language:PythonMIT27846 209 217

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

Language:PythonApache-2.021114 179 431

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.

Language:Jupyter NotebookNOASSERTION11192 92 305

threestudio

A unified framework for 3D content generation.

Language:PythonApache-2.06021 82 322

Vim

[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

Language:PythonApache-2.02690 30 102

PixArt-alpha

PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

Language:PythonAGPL-3.02613 460

fvcore

Collection of common code that's shared among different research projects in FAIR computer vision team.

Language:PythonApache-2.01958 41 79

FreeU

FreeU: Free Lunch in Diffusion U-Net (CVPR2024 Oral)

MIT1641 43 29

torchtitan

A native PyTorch Library for large model training

Language:PythonBSD-3-Clause1438 36 117

OpenDiT

OpenDiT: An Easy, Fast and Memory-Efficient System for DiT Training and Inference

Language:PythonApache-2.01392 23 57

FoundationPose

[CVPR 2024 Highlight] FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects

Language:PythonNOASSERTION1237 30 197

gangealing

Official PyTorch Implementation of "GAN-Supervised Dense Visual Alignment" (CVPR 2022 Oral, Best Paper Finalist)

Language:PythonBSD-2-Clause1010 16 37

masa

Official Implementation of CVPR24 highligt paper: Matching Anything by Segmenting Anything

Language:PythonApache-2.0913 59 21

accelerated_features

Implementation of XFeat (CVPR 2024). Do you need robust and fast local feature extraction? You are in the right place!

Language:Jupyter NotebookApache-2.0822 21 35

MVDream-threestudio

3D generation code for MVDream

Language:PythonApache-2.0468 19 28

FreeNeRF

[CVPR23] FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularization

Language:Python449 9 22

Open-MAGVIT2

Open-MAGVIT2: Democratizing Autoregressive Visual Generation

Language:PythonApache-2.0360 12 27

G.pt

Official PyTorch Implementation of "Learning to Learn with Generative Models of Neural Network Checkpoints"

Language:PythonBSD-2-Clause332 5 6

pqdm

Comfortable parallel TQDM using concurrent.futures

Language:PythonMIT273 3 14

EfficientTrain

1.5−3.0× lossless training or pre-training speedup. An off-the-shelf, easy-to-implement algorithm for the efficient training of foundation visual backbones.

Language:PythonMIT192 6 11

threestudio-3dgs

3D Gaussian Splatting extension of threestudio.

Language:Python155 7 16

rope-vit

[ECCV 2024] Official PyTorch implementation of RoPE-ViT "Rotary Position Embedding for Vision Transformer"

Language:PythonNOASSERTION120 12 2

FlowDiffusion_pytorch

Unofficial pytorch implementation of DDVM.

Language:PythonApache-2.075 4 2

einops-exts

Implementation of some personal helper functions for Einops, my most favorite tensor manipulation library ❤️

Language:PythonMIT53 4 1

CHOIR

Official source code of "Stable and Consistent Prediction of 3D Characteristic Orientation vis Invariant Residual Learning", ICML 2023

14 60

CorrespondentDream

Official PyTorch implementation of CorrespondentDream: Enhancing 3D Fidelity of Text-to-3D using Cross-View Correspondences (CVPR 2024 Poster)

Language:Python14 2 1

Sparsifiner

Demo code for CVPR2023 paper "Sparsifiner: Learning Sparse Instance-Dependent Attention for Efficient Vision Transformers"

Language:PythonMIT11 2 1

HCCNet

Official PyTorch implementation of HCCNet: Efficient Semantic Matching with Hypercolumn Correlation (WACV '24 Oral, Best paper finalist (top 0.6%))

Language:Python10 20

RIST

[CVPR 2024] Learning SO(3)-Invariant Semantic Correspondence via Local Shape Transform

MIT500