Tiankai Hang's repositories
Min-SNR-Diffusion-Training
[ICCV 2023] Efficient Diffusion Training via Min-SNR Weighting Strategy
language-guided-animation
Language-Guided Face Animation by Recurrent StyleGAN-based Generator
Awesome-Restoration
A list of restoration papers and repositories.
Awesome-Diffusion-Models
A collection of resources and papers on Diffusion Models and Score-based Models, a darkhorse in the field of Generative Models
azureml_docker
learn to make docker file for azureml
clean-fid
PyTorch - FID calculation with proper image resizing and quantization steps [CVPR 2022]
CLIP
Contrastive Language-Image Pretraining
Awesome-Video-Diffusion
A curated list of recent diffusion models for video generation, editing, restoration, understanding, etc.
DiT
Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"
edm-1
Elucidating the Design Space of Diffusion-Based Generative Models (EDM)
improved-aesthetic-predictor
CLIP+MLP Aesthetic Score Predictor
InstructDiffusion
[CVPR 2024] PyTorch implementation of InstructDiffusion, a unifying and generic framework for aligning computer vision tasks with human instructions.
misc-snippet
misc
OpenDiT-1
OpenDiT: An Easy, Fast and Memory-Efficient System for DiT Training and Inference
Paint-by-Example
Paint by Example: Exemplar-based Image Editing with Diffusion Models
PointCloudRenderer
Code for rendering the point cloud figures in paper: "PointFlow : 3D Point Cloud Generation with Continuous Normalizing Flows"
py12306
🚂 12306 购票助手,支持集群,多账号,多任务购票以及 Web 页面管理
pyprobml
Python code for "Probabilistic Machine learning" book by Kevin Murphy
pytorch-fid
Compute FID scores with PyTorch.
SciencePlots
Matplotlib styles for scientific plotting
score_sde_pytorch
PyTorch implementation for Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021, Oral)
StyleNeRF
This is the open source implementation of the ICLR2022 paper "StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesis"
VQ-Diffusion
Official implementation of VQ-Diffusion
webvid
Large-scale text-video dataset. 10 million captioned short videos.