fire2323

q-diffusion

[ICCV 2023] Q-Diffusion: Quantizing Diffusion Models.

fast-compress-vit

Official Pytorch Implementation of "A Fast Training-free Compression Framework for Vision Transformers"

get

Generative Equilibrium Transformer

T2T-ViT

ICCV2021, Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet

deit

Official DeiT repository

Awesome-Quantization-Papers

List of papers related to neural network quantization in recent AI conferences and journals.

DiffRate

[ICCV 23]An approach to enhance the efficiency of Vision Transformer (ViT) by concurrently employing token pruning and token merging techniques, while incorporating a differentiable compression rate.

VisionMamba

Implementation of Vision Mamba from the paper: "Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model" It's 2.8x faster than DeiT and saves 86.8% GPU memory when performing batch inference to extract features on high-res images

segmoe

comfy-todo

ImprovedTokenMerge

pytorch-OpCounter

Count the MACs / FLOPs of your PyTorch model.

HiDiffusion

[ECCV 2024] HiDiffusion: Increases the resolution and speed of your diffusion model by only adding a single line of code!

glow

Code for reproducing results in "Glow: Generative Flow with Invertible 1x1 Convolutions"

latent-consistency-model

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

celeba-hq-modified

Modified h5tool.py make user getting celeba-HQ easier

vqvae

A pytorch implementation of the vector quantized variational autoencoder (https://arxiv.org/abs/1711.00937)

make-CelebA-HQ

Supposed you've downloaded CelebA & CelebA-HQ dataset, and want to get HQ images from them.

progressive_growing_of_gans

Progressive Growing of GANs for Improved Quality, Stability, and Variation

torch-fidelity

High-fidelity performance metrics for generative models in PyTorch

PixelCNN

PyTorch implementation of gated PixelCNN

PixelCNN-Pytorch

A naive implementation of PixelCNN in Pytorch as described in A Oord et. al.

pytorchviz

A small package to create visualizations of PyTorch execution graphs

DL-Demos

Demos for deep learning

SwissRoll-VAE-pytorch

VAE model for approximating the distribution of the Swiss roll dataset.

PyTorch-VAE

A Collection of Variational Autoencoders (VAE) in PyTorch.

vae

a simple vae and cvae from keras

enhancing-transformers

An unofficial implementation of both ViT-VQGAN and RQ-VAE in Pytorch

gpt-2

Code for the paper "Language Models are Unsupervised Multitask Learners"

DALL-E

PyTorch package for the discrete VAE used for DALL·E.