Sumith1896

stable-diffusion

A latent text-to-image diffusion model

whisper

Robust Speech Recognition via Large-Scale Weak Supervision

rclone

"rsync for cloud storage" - Google Drive, S3, Dropbox, Backblaze B2, One Drive, Swift, Hubic, Wasabi, Google Cloud Storage, Azure Blob, Azure Files, Yandex Files

stablediffusion

High-Resolution Image Synthesis with Latent Diffusion Models

ComfyUI

The most powerful and modular stable diffusion GUI, api and backend with a graph/nodes interface.

nanoGPT

The simplest, fastest repository for training/finetuning medium-sized GPTs.

ControlNet

Let us control diffusion models!

generative-models

Generative Models by Stability AI

mae

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

fiftyone

The open-source tool for building high-quality datasets and computer vision models

lora

Using Low-rank adaptation to quickly fine-tune diffusion models.

instruct-pix2pix

DiT

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

eg3d

s4

Structured state space sequence models

k-diffusion

Karras et al. (2022) diffusion models for PyTorch

consistencydecoder

Consistency Distilled Diff VAE

MineDojo

Building Open-Ended Embodied Agents with Internet-Scale Knowledge

invisible-watermark

python library for invisible image watermark (blind image watermark)

edm

Elucidating the Design Space of Diffusion-Based Generative Models (EDM)

4D-Humans

4DHumans: Reconstructing and Tracking Humans with Transformers

clean-fid

PyTorch - FID calculation with proper image resizing and quantization steps [CVPR 2022]

muse-maskgit-pytorch

Implementation of Muse: Text-to-Image Generation via Masked Generative Transformers, in Pytorch

BlenderToolbox

Some simple Blender scripts for rendering paper figures

video2dataset

Easily create large video dataset from video urls

aesthetic-predictor

A linear estimator on top of clip to predict the aesthetic quality of pictures

maskgit

Official Jax Implementation of MaskGIT

mlc-en

recurrent-interface-network-pytorch

Implementation of Recurrent Interface Network (RIN), for highly efficient generation of images and video without cascading networks, in Pytorch

fastGPT

Fast GPT-2 inference written in Fortran