Open-Sora: Democratizing Efficient Video Production for All

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

[ECCV 2024, Oral] DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors

InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Implementation of 🌻 Mirasol, SOTA Multimodal Autoregressive model out of Google Deepmind, in Pytorch

ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型

Chinese and English multimodal conversational language model | 多模态中英双语对话语言模型

Stable Diffusion web UI

[ICCV 2023] Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation

Official implementation of AnimateDiff.

A curated list of recent diffusion models for video generation, editing, restoration, understanding, etc.

[ICLR 2024] Official pytorch implementation of "ControlVideo: Training-free Controllable Text-to-Video Generation"

C++ model train&inference framework

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

Usable Implementation of "Bootstrap Your Own Latent" self-supervised learning, from Deepmind, in Pytorch

A data augmentations library for audio, image, text, and video.

记录state-of-art计算机视觉相关论文。

Caffe Implementation of Google's MobileNets (v1 and v2)

Memory consumption and FLOP count estimates for convnets

pytorch version of SSD and it's enhanced methods such as RFBSSD,FSSD and RefineDet

Context-driven data augmentation for Object Detection (ECCV'18)

PyTorch implementations of Generative Adversarial Networks.

An Open Source Machine Learning Framework for Everyone

Monitoring system clipboard change and joining multi-line text. It's very useful when copying multi-line text from PDF files.

MATLAB Implementation of Harmony Search, a nature inspired optimization algorithm

[Unmaintained] Say Hi to your new followers in Zhihu.