Open-Sora-Plan
AI Model Reproduction Project
An open-source project aiming to reproduce the capabilities of a cutting-edge AI model using Python and Huawei Ascend AI computing system
This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.
12k stars
155 watching
1k forks
Language: Python
last commit: almost 2 years agoRelated projects:
| Repository | Description | Stars |
|---|---|---|
 thudm/cogvideo | Generates videos from text and images using large language models | 9,761 |
 tachibanayoshino/animeganv2 | A tool that generates anime styles from landscape photos and videos using deep learning techniques. | 5,118 |
 nvidia/vid2vid | A PyTorch implementation of a video-to-video translation method for generating photorealistic videos from semantic label maps or other input data. | 8,623 |
| pku-yuangroup/open-sora-dataset | A large video dataset collected from various open-source websites for use in computer vision and multimedia applications. | 94 |
 hachinobu/samuraitransition | An animation-based library providing a range of transition animations for ViewControllers in Swift. | 279 |
 transitive-bullshit/ffmpeg-generate-video-preview | Generates image strips or GIFs from video files | 153 |
| pku-yuangroup/magictime | Generates time-lapse videos from text inputs using deep learning models. | 1,312 |
 aliaksandrsiarohin/first-order-model | This project provides a deep learning framework for animating images with motion transfer from driving videos. | 14,599 |
| tachibanayoshino/animegan | Generates anime-style images from real-world photos using a deep learning model. | 4,502 |
| pku-yuangroup/chronomagic-bench | Provides a benchmarking framework for evaluating the quality of text-to-video generation models | 191 |
| transitive-bullshit/ffmpeg-gl-transition | A library that enables easy application of GLSL transitions between video streams in FFmpeg filter graphs | 673 |
 hvision-nku/storydiffusion | This project provides an implementation of a self-attention mechanism for long-range image and video generation, enabling the creation of consistent narratives. | 6,030 |
 gitcvfb/rssr | Software tool to invert rolling shutter camera images and generate high framerate global shutter video | 35 |
 pkhungurn/talking-head-anime-demo | Creates anime characters with realistic head movements from single images or webcam feeds using deep learning and computer vision techniques. | 2,001 |
 one-2-3-45/one-2-3-45 | An open-source project that enables the generation of 3D mesh models from single images in under a minute. | 1,582 |