Stars
A Simple but Effective Downsampling Module For Semantic Segmentation
SUNet: Swin Transformer with UNet for Image Denoising
[CVPR 2022] StyleSwin: Transformer-based GAN for High-resolution Image Generation
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
It is a fine-grained weed recognition using Swin Transformer and a contrastive loss
Contrastive unpaired image-to-image translation, faster and lighter training than cyclegan (ECCV 2020, in PyTorch)
Image-to-Image Translation in PyTorch
High-Resolution Image Synthesis with Latent Diffusion Models
[CVPR 2023] Executing your Commands via Motion Diffusion in Latent Space, a fast and high-quality motion diffusion model
deep learning for image processing including classification and object-detection etc.
Implementation of Axial attention - attending to multi-dimensional data efficiently
A better PyTorch implementation of image local attention which reduces the GPU memory by an order of magnitude.
Implementation of Medfusion - A latent diffusion model for medical image synthesis.
Stable Diffusion PyTorch Implementation
Conditional denoising diffusion probabilistic model trained in latent space.
This may be the simplest implement of DDPM. You can directly run Main.py to train the UNet on CIFAR-10 dataset and see the amazing process of denoising.
implementation of classifier-free diffusion guidance and notes about some important formulas in diffusion models
PyTorch Implementation of V-objective Diffusion Probabilistic Models with Classifier-free Guidance
a simple unofficial implementation of classifier-free diffusion guidance
Classifier-Free Guidance Diffusion Model for MNIST Generation
Medical brain MRI image generation with stable-diffusion model
Stable Diffusion for Medical Images
jorge-pessoa / pytorch-msssim
Forked from Po-Hsun-Su/pytorch-ssimPyTorch differentiable Multi-Scale Structural Similarity (MS-SSIM) loss