Pytorch implementation of "Light Schrödinger Bridge" (ICLR 2024)

Framework for processing and filtering datasets

KandinskyVideo — multilingual end-to-end text2video latent diffusion model

Kandinsky x Deforum — generating short animations

Kandinsky 2 — multilingual text2image latent diffusion model

Real-time face swap for PC streaming or video calls

GENA-LM is a transformer masked language model trained on human DNA sequence.

nablaDFT: Large-Scale Conformational Energy and Hamiltonian Prediction benchmark and dataset

eco2AI is a python library which accumulates statistics about power consumption and CO2 emission during running code.

FusionBrain Challenge 2.0: creating multimodal multitask model

HAnd Gesture Recognition Image Dataset

Fast and customizable framework for automatic ML model creation (AutoML)

Generate images from texts. In Russian

HAnd Gesture Recognition Image Dataset

A library built upon PyTorch for building embeddings on discrete event sequences using self-supervision

LAMA - automatic model creation framework

Easily compute clip embeddings and build a clip retrieval system with them

A new one shot face swap approach for image and video domains

RUDOLPH: One Hyper-Tasking Transformer can be creative as DALL-E and GPT-3 and smart as CLIP

Repository containing our datasets for HTR (handwritten text recognition) task.

An easy-to-run OCR model pipeline based on CRNN and CTC loss

Handwritten Text Generation

AI Journey Contest 2021: AITrain

AI Journey Contest 2021: NoFireWithAI

BERT-NER (nert-bert) with google bert https://github.com/google-research.