Stable Diffusion in TensorFlow / Keras

Implementation of self-supervised image-level contrastive pretraining methods using Keras.

Implementation of denoising diffusion models with schedules, improved sampling, and other extensions using Keras.

Hands-On Data Visualization: Interactive Storytelling from Spreadsheets to Code is an open-access book, also published with O'Reilly Media.

Generalized AI to perform a multitude of tasks written in python3

Supercharge Your Model Training

A centralized place for deep thinking code and experiments

Create an artificial neural network in Blender

Pure Python (no additional dependencies) helper module to read metadata from the header of OpenEXR files.

Author's implementation of Learning a Family of Motor Skills from a Single Motion Clip (SIGGRAPH 2021 Technical Paper)

PyTorch implementation of UPFlow (unsupervised optical flow learning)

Implements sharpness-aware minimization (https://arxiv.org/abs/2010.01412) in TensorFlow 2.

An analysis of hooktheory's db, represented as a sankey plot

Node-based multi-line text and image flowchart

Dense matching library based on PyTorch

🖼✨Automatically generates line drawing from a photograph

A sketch extractor for anime/illustration.

pip install antialiased-cnns to improve stability and accuracy

Reproducing images with geometric primitives.

sketch + style = paints 🎨 (TOG2018/SIGGRAPH2018ASIA)

An interactive demo application for the algorithm proposed in our SIGGRAPH Asia 2017 technical paper.

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

Official SRFlow training code: Super-Resolution using Normalizing Flow in PyTorch

Official pytorch implementation of the paper: "Ultrafast Photorealistic Style Transfer via Neural Architecture Search"

HDR image reconstruction from a single exposure using deep CNNs

Official PyTorch implementation of "Single Image HDR Reconstruction Using a CNN with Masked Features and Perceptual Loss" (SIGGRAPH 2020)

Real-Time High-Resolution Background Matting

Sample-based Monte Carlo Denoising using a Kernel-Splatting Network [Siggraph 2019]