Pinned Repositories
3DTopia
Text-to-3D Generation within 5 Minutes
4BHKDuplex
AiOS
[CVPR 2024] Official Code for "AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation
BackgroundMattingV2
Real-Time High-Resolution Background Matting
contact-human-dynamics
Code for ECCV 2020 paper "Contacts and Human Dynamics from Monocular Video".
DreamCraft3D
[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior
FluxMusic
Text-to-Music Generation with Rectified Flow Transformers
GaussianHaircut
Gaussian Haircut: Human Hair Reconstruction with Strand-Aligned 3D Gaussians
gigagan-pytorch
Implementation of GigaGAN, new SOTA GAN out of Adobe. Culmination of nearly a decade of research into GANs
ICON
[CVPR'22] ICON: Implicit Clothed humans Obtained from Normals
Stevezant's Repositories
Stevezant/BackgroundMattingV2
Real-Time High-Resolution Background Matting
Stevezant/3DTopia
Text-to-3D Generation within 5 Minutes
Stevezant/4BHKDuplex
Stevezant/AiOS
[CVPR 2024] Official Code for "AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation
Stevezant/contact-human-dynamics
Code for ECCV 2020 paper "Contacts and Human Dynamics from Monocular Video".
Stevezant/DreamCraft3D
[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior
Stevezant/FluxMusic
Text-to-Music Generation with Rectified Flow Transformers
Stevezant/GaussianHaircut
Gaussian Haircut: Human Hair Reconstruction with Strand-Aligned 3D Gaussians
Stevezant/gigagan-pytorch
Implementation of GigaGAN, new SOTA GAN out of Adobe. Culmination of nearly a decade of research into GANs
Stevezant/ICON
[CVPR'22] ICON: Implicit Clothed humans Obtained from Normals
Stevezant/InstantMesh
InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models
Stevezant/magic-animate
MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model
Stevezant/Mangio-RVC-Fork
*CREPE+HYBRID TRAINING* A very experimental fork of the Retrieval-based-Voice-Conversion-WebUI repo that incorporates a variety of other f0 methods, along with a hybrid f0 nanmedian method.
Stevezant/MagicQuill
Official Implementations for Paper - MagicQuill: An Intelligent Interactive Image Editing System
Stevezant/PantoMatrix
PantoMatrix: Co-Speech Talking Head and Gestures Generation
Stevezant/RexSeek
Referring any person or objects given a natural language description. Code base for RexSeek and HumanRef Benchmark
Stevezant/roop
Based9Based version of ROOP, No NSFW Filter, No ERRORS ;)
Stevezant/StreamingT2V
StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text
Stevezant/The_Lightmapper
Fast and easy baked GI Lightmaps for Blender and Cycles
Stevezant/threestudio
A unified framework for 3D content generation.
Stevezant/unique
single image
Stevezant/VideoPose3D
Efficient 3D human pose estimation in video using 2D keypoint trajectories
Stevezant/Wonder3D
Single Image to 3D using Cross-Domain Diffusion for 3D Generation