kelisiya

TIMI-Net

server

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

Bringing-Old-Photos-Back-to-Life

Bringing Old Photo Back to Life (CVPR 2020 oral)

CodeFormer

[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer

ControlNet

Let us control diffusion models

ControlNet-for-Diffusers

Transfer the ControlNet with any basemodel in diffusers🔥

ControlNet-v1-1-nightly

Nightly release of ControlNet 1.1

DBPN-Pytorch

The project is an official implement of our CVPR2018 paper "Deep Back-Projection Networks for Super-Resolution" (Winner of NTIRE2018 and PIRM2018)

deepsvg

Official code for the paper "DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation". Includes a PyTorch library for deep learning with SVG data.

diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

ELLA

ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment

ESRGAN

ECCV18 Workshops - Enhanced SRGAN. Champion PIRM Challenge on Perceptual Super-Resolution. The training codes are in BasicSR.

GFM

[IJCV 2022] Bridging Composite and Real: Towards End-to-end Deep Image Matting

google-research

Google Research

GPEN

Im2Vec

[CVPR 2021 Oral] Im2Vec Synthesizing Vector Graphics without Vector Supervision

Image-Super-Resolution-via-Iterative-Refinement

Unoffical implementation about Image Super-Resolution via Iterative Refinement by Pytorch

JARVIS

JARVIS, a system to connect LLMs with ML community

kelisiya.github.io

My personal homepage

mmediting

OpenMMLab Image and Video Editing Toolbox

oomstore

A Fast Feature Store Powered by Go.

python_backend

Triton backend that enables pre-process, post-processing and other logic to be implemented in Python.

Real-ESRGAN

Real-ESRGAN aims at developing Practical Algorithms for General Image Restoration.

RepVGG

RepVGG: Making VGG-style ConvNets Great Again

stable-diffusion-webui

Stable Diffusion web UI

TCVC-Temporally-Consistent-Video-Colorization

Temporally Consistent Video Colorization with Deep Feature Propagation and Self-regularization Learning

TensorRT

NVIDIA® TensorRT™, an SDK for high-performance deep learning inference, includes a deep learning inference optimizer and runtime that delivers low latency and high throughput for inference applications.

torch2trt

An easy to use PyTorch to TensorRT converter

Yolov3_Dynamic_Batch_TensorRT_Triton

将Yolov3模型转成可以进行动态Batch的TensorRT推理以及Triton Inference Serving上部署的TensorRT模型

yolov5-face

YOLO5Face: Why Reinventing a Face Detector (https://arxiv.org/abs/2105.12931)