Stars
为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…
Generative Models by Stability AI
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
Official implementation of AnimateDiff.
[CVPR 2024] Official repository for "MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model"
Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.
A PyTorch implementation of EfficientNet
The GitHub repository for the paper "Informer" accepted by AAAI 2021.
PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722
VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models
[ECCV 2024] Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance
Differentiable architecture search for convolutional and recurrent networks
VMamba: Visual State Space Models，code is based on mamba
Unofficial PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners
[NeurIPS 2025] YOLOv12: Attention-Centric Real-Time Object Detectors
A simple and efficient Mamba implementation in pure PyTorch and MLX.
✨ Hotshot-XL: State-of-the-art AI text-to-GIF model trained to work alongside Stable Diffusion XL
[ICML 2024] MagicPose(also known as MagicDance): Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusion
Official Code for "Non-deep Networks"
[NeurIPS 2025 Spotlight] ReasonFlux Series - ReasonFlux, ReasonFlux-PRM and ReasonFlux-Coder
vHeat: Building Vision Models upon Heat Conduction
(CVPR2023/TPAMI2024) Integrally Pre-Trained Transformer Pyramid Networks -- A Hierarchical Vision Transformer for Masked Image Modeling
Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Search
A toolbox for object skeleton detection, can also be used for edge detection, building extraction and road extraction. TIP (2021)
[CVPR 2025] Adaptive Keyframe Sampling for Long Video Understanding
[Neurocomputing] The official code for "H-vmunet: High-order Vision Mamba UNet for Medical Image Segmentation".
[AAAI2025] ChatterBox: Multi-round Multimodal Referring and Grounding, Multimodal, Multi-round dialogues