mxtx0509
Follow
Stars
Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
collection of diffusion model papers categorized by their subareas
Official PyTorch implementation of ECCV 2024 Paper: ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback.
Code for Deep Single-image Portrait Image Relighting
[AAAI 2025] Official codes of "ResAdapter: Domain Consistent Resolution Adapter for Diffusion Models".
The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.
Stable Diffusion in NCNN with c++, supported txt2img and img2img
Face Pose: Estimate pose (Yaw, Roll, Pitch) of a face using two extremely simple, efficient and accurate methods.
StyleSwap: Style-Based Generator Empowers Robust Face Swapping (ECCV 2022)
Unofficial implementation of the paper: StyleSwap: Style-Based Generator Empowers Robust Face Swapping
Stable Diffusion web UI
Real time yolox Android demo by ncnn
Adaptive Feature Fusion Network for Gaze Tracking in Mobile Tablets.
Official repo of RepOptimizers and RepOpt-VGG
label-smooth, amsoftmax, partial-fc, focal-loss, triplet-loss, lovasz-softmax. Maybe useful
AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
YOLO5Face: Why Reinventing a Face Detector (https://arxiv.org/abs/2105.12931) ECCV Workshops 2022)
State-of-the-art 2D and 3D Face Analysis Project
UMT is a unified and flexible framework which can handle different input modality combinations, and output video moment retrieval and/or highlight detection results.
Implementation of Cross-category Video Highlight Detection via Set-based Learning (ICCV 2021).