Minimal Implementation of a D3PM in pytorch

Huggingface-compatible SDXL Unet implementation that is readily hackable

[ICLR 2023] RC-MAE

Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and 🔜 video, up to 5x faster than OpenAI CLIP and LLaVA 🖼️ & 🖋️

Let us control diffusion models!

Stable Diffusion web UI

Making large AI models cheaper, faster and more accessible

Command-line program to download videos from YouTube.com and other video sites

A collection of resources and papers on Diffusion Models

Guide to using pre-trained large language models of source code

Instant neural graphics primitives: lightning fast NeRF and more

[CVPR 2022] MPViT:Multi-Path Vision Transformer for Dense Prediction

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Scenic: A Jax Library for Computer Vision Research and Beyond

Template repository to build PyTorch projects from source on any version of PyTorch/CUDA/cuDNN.

Data augmentation for NLP

텍스트 요약 분야의 주요 연구 주제, Must-read Papers, 이용 가능한 model 및 data 등을 추천 자료와 함께 정리한 저장소입니다.

A curated list of resources for NLP (Natural Language Processing) for Korean

DialogSum: A Real-life Scenario Dialogue Summarization Dataset - Findings of ACL 2021

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

[Zoom & Facebook Live] Weekly AI Arxiv 시즌2

[NeurIPS 2021 Spotlight] Official code for "Focal Self-attention for Local-Global Interactions in Vision Transformers"

Semi-Supervised Learning, Object Detection, ICCV2021

Genalog is an open source, cross-platform python package allowing generation of synthetic document images with custom degradations and text alignment capabilities.

PyTorch Lightning + Hydra. A very user-friendly template for ML experimentation. ⚡🔥⚡

PyTorch to TensorFlow Lite converter