Roman's starred repositories
gan-compression
[CVPR 2020] GAN Compression: Efficient Architectures for Interactive Conditional GANs
tuning_playbook
A playbook for systematically maximizing the performance of deep learning models.
stable-fast
Best inference performance optimization framework for HuggingFace Diffusers on NVIDIA GPUs.
Moore-AnimateAnyone
Character Animation (AnimateAnyone, Face Reenactment)
StreamDiffusion
StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation
CloneCleaner
An extension for Automatic1111 to work around Stable Diffusion's "clone problem". It automatically modifies your prompts with random names, nationalities, hair style and hair color to create more variations in generated people.
TokenMixer
An A1111 extension for interpolating tokens into embeddings
hookandlook
A library helping to gather stats and run checks during training deep learning models with Pytorch
stylegan3-editing
Official Implementation of "Third Time's the Charm? Image and Video Editing with StyleGAN3" (AIM ECCVW 2022) https://arxiv.org/abs/2201.13433
deepfillv2-pytorch
A PyTorch reimplementation of the paper Free-Form Image Inpainting with Gated Convolution (DeepFill v2) (https://arxiv.org/abs/1806.03589)
AttGAN-Tensorflow
AttGAN: Facial Attribute Editing by Only Changing What You Want (IEEE TIP 2019)
pixel-guided-diffusion
Fine-grained Image Editing by Pixel-wise Guidance Using Diffusion Models
efficient-dl-systems
Efficient Deep Learning Systems course materials (HSE, YSDA)
generative-models
Generative Models by Stability AI
Efficient-Segmentation-Networks
Lightweight models for real-time semantic segmentationon PyTorch (include SQNet, LinkNet, SegNet, UNet, ENet, ERFNet, EDANet, ESPNet, ESPNetv2, LEDNet, ESNet, FSSNet, CGNet, DABNet, Fast-SCNN, ContextNet, FPENet, etc.)
awesome_lightweight_networks
The implementation of various lightweight networks by using PyTorch. such as:MobileNetV2,MobileNeXt,GhostNet,ParNet,MobileViT、AdderNet,ShuffleNetV1-V2,LCNet,ConvNeXt,etc. ⭐⭐⭐⭐⭐
bitsandbytes
Accessible large language models via k-bit quantization for PyTorch.