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

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

Styled text-to-drawing synthesis method. Featured at the 2021 NeurIPS Workshop on Machine Learning for Creativity and Design

Unpaired line drawing generation

Barbershop: GAN-based Image Compositing using Segmentation Masks (SIGGRAPH Asia 2021)

Text-to-Image generation. The repo for NeurIPS 2021 paper "CogView: Mastering Text-to-Image Generation via Transformers".

Official Implementation for "StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery" (ICCV 2021 Oral)

a machine learning image inpainting task that instinctively removes watermarks from image indistinguishable from the ground truth image

Search images with a text or image query, using Open AI's pretrained CLIP model.

General Virtual Sketching Framework for Vector Line Art (SIGGRAPH 2021)

Takes an image as input and generates drawing (Path) instructions. It then draws that image in MS Paint or any other canvas using the mouse.

This github contains the network architectures of NeuralVoicePuppetry.

💇🏻‍♀️ An end-to-end workflow for editing hair attributes on real faces

Wind Turbine Object Detection from Aerial Imagery Using TensorFlow Object Detection API and Google Colab

This is the open-source project Avatar-GAN from the paper RoboCoDraw: Robotic Avatar Drawing with GAN-based Style Transfer andTime-efficient Path Optimization published in AAAI 2020

Code for Photo-Sketching: Inferring Contour Drawings from Images 🐶

The source code of CVPR19 'Im2Pencil: Controllable Pencil Illustration from Photographs'.

Photoshop script to quickly replace shapes with images.