Stars
PyTorch Lightning + Hydra. A very user-friendly template for ML experimentation. ⚡🔥⚡
HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation
UniAnimate-DiT: Human Image Animation with Large-Scale Video Diffusion Transformer
Qwen-Image-Lightning: Speed up Qwen-Image model with distillation
🔥🔥🔥 Set the world of 3D faces on fire with INFERNO 🔥🔥🔥
[CVPR 2024 Highlight] The official repo for "GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians"
Official implementation of the paper "GUAVA: Generalizable Upper Body 3D Gaussian Avatar" [ICCV 2025]
HyperMotion is a pose guided human image animation framework based on a large-scale video diffusion Transformer.
[CAAI AIR'24] Bilateral Reference for High-Resolution Dichotomous Image Segmentation
[NeurIPS 2024] Generalizable Implicit Motion Modeling for Video Frame Interpolation
ABME AdaFNIO AMT BiM-VFI BiT CBBD CDFI CtxSyn DBVI DC-BVFI DQBC DRVI DvP EAFI EBME EDC EDEN EDENVFI EDSC EMA-VFI FGDCN FILM FLAVR GIMM-VFI HFD HiFI H-VFI IFRNet InterpAny-Clearer IQ-VFI JNMR LADDER…
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
[CVPR 2024 Highlight] Putting the Object Back Into Video Object Segmentation
[ICCV2025] LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds
[SIGGRAPH'25] SOAP: Style-Omniscient Animatable Portraits
[SIGGRAPH 2025] Official code of the paper "FlexiAct: Towards Flexible Action Control in Heterogeneous Scenarios"
[ACM MM 2025] FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
2025年11月更新，目前国内可用Docker镜像源汇总，DockerHub国内镜像加速列表，🚀DockerHub镜像加速器
[SIGGRAPH 2025] LAM: Large Avatar Model for One-shot Animatable Gaussian Head
3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting
Code for our CVPR 2019 work.