Kuma's repositories
Rethinking-Inpainting-MEDFE
Rethinking Image Inpainting via a Mutual Encoder Decoder with Feature Equalizations. ECCV 2020 Oral
HeadArtist
The official code of HeadArtist: Text-conditioned 3D Head Generation with Self Score Distillation
Human-MotionFormer
The official code of Human MotionFormer: Transferring Human Motions with Vision Transformers, ICLR2023
KumaInpainting
Kumainpainting is an open source image inpainting toolbox based on PyTorch, integrating the four methods we proposed.
gangealing
Official PyTorch Implementation of GAN-Supervised Dense Visual Alignment
Bringing-Old-Photos-Back-to-Life
Bringing Old Photo Back to Life (CVPR 2020 oral)
copilot-docs
Documentation for GitHub Copilot
diffusion-point-cloud
:thought_balloon: Diffusion Probabilistic Models for 3D Point Cloud Generation (CVPR 2021)
gansformer
Generative Adversarial Transformers
glide-text2im
GLIDE: a diffusion-based text-conditional image synthesis model
KumapowerLIU.github.io
AcadHomepage: A Modern and Responsive Academic Personal Homepage
mesh-fusion
Python tool for obtaining watertight meshes using TSDF fusion.
MM-CelebA-HQ-Dataset
[CVPR 2021] A large-scale face image dataset that allows text-to-image generation, text-guided image manipulation, sketch-to-image generation, GANs for face generation and editing, image caption, and VQA
multidiffusion-upscaler-for-automatic1111
Tiled Diffusion and VAE optimize, licensed under CC BY-NC-SA 4.0
system-design-primer
Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.
Tex-An_Mesh
Fully textured and animatable human body mesh reconstruction from a single image
train-CLIP
A PyTorch Lightning solution to training OpenAI's CLIP from scratch.
x-transformers
A simple but complete full-attention transformer with a set of promising experimental features from various papers