Khoi Nguyen's repositories
2d-gaussian-splatting
[SIGGRAPH'24] 2D Gaussian Splatting for Geometrically Accurate Radiance Fields
6Img-to-3D
Few-Image to 3D Method
B-LoRA
Implicit Style-Content Separation using B-LoRA
champ
Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance
drkhoinguyen.github.io
My academic website
FeatUp
Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024
GaussianAvatar
Official repo for "GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians"
GenerateU
[CVPR2024] Generative Region-Language Pretraining for Open-Ended Object Detection
GPAvatar
[ICLR 2024] Generalizable and Precise Head Avatar from Image(s)
IDM-VTON
IDM-VTON : Improving Diffusion Models for Authentic Virtual Try-on in the Wild
img2img-turbo
One-step image-to-image with Stable Diffusion turbo: sketch2image, day2night, and more
InstantMesh
InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models
Magic-Me
Codes for ID-Specific Video Customized Diffusion
multi-hmr
Pytorch demo code and models for Multi-HMR
MusePose
MusePose: a Pose-Driven Image-to-Video Framework for Virtual Human Generation
OccSora
OccSora: 4D Occupancy Generation Models as World Simulators for Autonomous Driving
OOTDiffusion
Official implementation of OOTDiffusion
Perturbed-Attention-Guidance
Official implementation of "Perturbed-Attention Guidance"
PlainMamba
PlainMamba: Improving Non-hierarchical Mamba in Visual Recognition
PSALM
This is an official implementation for "PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model"
SEED-X
Multimodal Models in Real World
StableVITON
[CVPR2024] StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On
Unique3D
Official implementation of Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image
VMamba
VMamba: Visual State Space Models,code is based on mamba