Fine-tune FLUX-dev ControlNet on a single A100 40GB GPU.

Multi-view datasets for classification or clustering

CVPR2023 | MVImgNet: A Large-scale Dataset of Multi-view Images

Robust Human Matting via Semantic Guidance, ACCV 2022.

Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audi…

SPIGA: Shape Preserving Facial Landmarks with Graph Attention Networks.

A sample application of how to use the NDK and OpenCV to make a basic classifier using PyTorch Mobile models.

A lightweight, dependency-free Python library (and command-line utility) for downloading YouTube Videos.

Adapted from https://note.com/kohya_ss/n/nbf7ce8d80f29 for easier cloning

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

This repository contains demos I made with the Transformers library by HuggingFace.

Efficient few-shot learning with Sentence Transformers

Build and run Docker containers leveraging NVIDIA GPUs

Serve, optimize and scale PyTorch models in production

Karras et al. (2022) diffusion models for PyTorch

High-Resolution Image Synthesis with Latent Diffusion Models

A latent text-to-image diffusion model

Face synthetics datasets

A motion generation model learned from a single example [SIGGRAPH 2022]

Inspired by Hillebrand & Medeiros (2009) and Corsi (2009), I put neural networks in a High frequency environment, and tested the performance of the two models (HAR & Neural Networks). - The data us…

Official code for the CVPR 2022 (oral) paper "Extracting Triangular 3D Models, Materials, and Lighting From Images".

Optimization based style transfer

A machine learning-based video super resolution and frame interpolation framework. Est. Hack the Valley II, 2018.

Blind Face Restoration via Deep Multi-scale Component Dictionaries (ECCV 2020)

Winning Solution in NTIRE19 Challenges on Video Restoration and Enhancement (CVPR19 Workshops) - Video Restoration with Enhanced Deformable Convolutional Networks. EDVR has been merged into BasicSR…