FaceChain is a deep-learning toolchain for generating your Digital-Twin.

Official repo for VGen: a holistic video generation ecosystem for video generation building on diffusion models

VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs

Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion

TorchCFM: a Conditional Flow Matching library

Towards Better Stability and Adaptability: Improve Online Self-Training for Model Adaptation in Semantic Segmentation(CVPR-2023)

Fuzzy Positive Learning (CVPR2023)

Official PyTorch Code for "Spatio-Temporal Pixel-Level Contrastive Learning-based Source-Free Domain Adaptation for Video Semantic Segmentation" (CVPR 2023)

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

A latent text-to-image diffusion model

[CVPR 2023] Out-of-Distributed Semantic Pruning for Robust Semi-Supervised Learning

[CVPR 2021] CPS: Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision

[ECCV 2022] Implementation of the paper "Locality Guidance for Improving Vision Transformers on Tiny Datasets"