wtmarvel

stable-diffusion

A latent text-to-image diffusion model

Fooocus

Focus on prompting and generating

generative-models

Generative Models by Stability AI

llama2.c

Inference Llama 2 in one file of pure C

codellama

Inference code for CodeLlama models

flash-attention

Fast and memory-efficient exact attention

tiktoken

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

seamless_communication

Foundational Models for State-of-the-Art Speech and Text Translation

Yi

A series of large language models trained from scratch by developers @01-ai

TinyLlama

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

consistency_models

Official repo for consistency models.

CogVLM

a state-of-the-art-level open visual language model | 多模态预训练模型

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

CoDeF

[CVPR 2024 Highlight] Official PyTorch implementation of CoDeF: Content Deformation Fields for Temporally Consistent Video Processing

latent-consistency-model

Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference

FaceDetection-DSFD

腾讯优图高精度双分支人脸检测器

Open-AnimateAnyone

Unofficial Implementation of Animate Anyone

vector-quantize-pytorch

Vector (and Scalar) Quantization, in Pytorch

DragGAN

Implementation of DragGAN: Interactive Point-based Manipulation on the Generative Image Manifold

pythia

The hub for EleutherAI's work on interpretability and learning dynamics

webdataset

A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.

Candle

GRBL controller application with G-Code visualizer written in Qt.

voxceleb_trainer

In defence of metric learning for speaker recognition

VanillaNet

AcademiCodec

AcademiCodec: An Open Source Audio Codec Model for Academic Research

DPE

[CVPR 2023] DPE: Disentanglement of Pose and Expression for General Video Portrait Editing

vampnet

music generation with masked transformers!

AttentionIsOFFByOne

Implementation of "Attention Is Off By One" by Evan Miller

HADAR

This is an LWIR stereo-hyperspectral database to develop HADAR algorithms for thermal navigation. Based on this database, one can develop algorithms for TeX decomposition to generate TeX vision. One can also develop algorithms about object detection, semantic or scene segmentation, optical or scene flow, stereo depth etc. based on TeX vision instead of traditional RGB or thermal vision.

TTS-TextAnalyzer

TTS Text Analyzer