Dress Code: High-Resolution Multi-Category Virtual Try-On. ECCV 2022

More relighting!

StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation

Draw perfect pressure-sensitive freehand lines.

Unofficial implementation of RealFill

[Information Fusion (Vol.103, Mar. '24)] Boosting Image Matting with Pretrained Plain Vision Transformers

[ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with Hierarchical Attention

Code for the paper "Training Diffusion Models with Reinforcement Learning"

Auto detecting, masking and inpainting with detection model.

PyTorch code and models for the DINOv2 self-supervised learning method.

SoftVC VITS Singing Voice Conversion

A method to increase the speed and lower the memory footprint of existing vision transformers.

Implementation of GigaGAN, new SOTA GAN out of Adobe. Culmination of nearly a decade of research into GANs

Code and models for the paper "One Transformer Fits All Distributions in Multi-Modal Diffusion"

Official implementation of "Composer: Creative and Controllable Image Synthesis with Composable Conditions"

🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch

Open-vocabulary Object Segmentation with Diffusion Models

fastdup is a powerful, free tool designed to rapidly generate valuable insights from image and video datasets. It helps enhance the quality of both images and labels, while significantly reducing d…

Implementation of 🦩 Flamingo, state-of-the-art few-shot visual question answering attention net out of Deepmind, in Pytorch

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

Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch

PyTorch implementation for SDEdit: Image Synthesis and Editing with Stochastic Differential Equations

SwinIR: Image Restoration Using Swin Transformer (official repository)

Converted CoreML Model Zoo.