ddbourgin

stable-diffusion

A latent text-to-image diffusion model

tuning_playbook

A playbook for systematically maximizing the performance of deep learning models.

generative_agents

Generative Agents: Interactive Simulacra of Human Behavior

tortoise-tts

A multi-voice TTS system trained with an emphasis on quality

mesh-transformer-jax

Model parallel transformers in JAX and Haiku

guided-diffusion

BLIP

PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

discoart

🪩 Create Disco Diffusion artworks in one line

glide-text2im

GLIDE: a diffusion-based text-conditional image synthesis model

vector-quantize-pytorch

Vector (and Scalar) Quantization, in Pytorch

k-diffusion

Karras et al. (2022) diffusion models for PyTorch

karateclub

Karate Club: An API Oriented Open-source Python Framework for Unsupervised Learning on Graphs (CIKM 2020)

score_sde

Official code for Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021, Oral)

diffusiondb

A large-scale text-to-image prompt gallery dataset based on Stable Diffusion

restyle-encoder

Official Implementation for "ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement" (ICCV 2021) https://arxiv.org/abs/2104.02699

nnsvs

Neural network-based singing voice synthesis library for research

Video-P2P

Video-P2P: Video Editing with Cross-attention Control

latentblending

Create butter-smooth transitions between prompts, powered by stable diffusion

OMR-Datasets

Collection of datasets used for Optical Music Recognition

genalog

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

autoencoding_vi_for_topic_models

Tensorflow implementation for prodLDA and NVLDA.

nested-tuplets

Fancy javascript for manipulating nested tuplets

clpcnet

Pitch-shifting, time-stretching, and vocoding of speech with Controllable LPCNet (CLPCNet)

valentine

An open source compressor meant to pump and breathe

pink-trombone

Pink Trombone exhibit by Neil Thapen

choices13k

PIH

probably

Approximate computing algorithms

bwaa-bwaa

An easy-to-use, standalone music server for your browser

audio-sample-gen

Generate audio sampler automatically for training neural nets.