Open-Sora-Plan

An open-source project aiming to reproduce OpenAI's Sora (T2V model) and build knowledge about Video-VQVAE (VideoGPT) + DiT.

CommonProductProgrammingOpen-source projectAI model reproduction

Visit

Open-Sora-Plan is an open-source project dedicated to replicating OpenAI's Sora (T2V model) and constructing knowledge about Video-VQVAE (VideoGPT) + DiT. Initiated by the Peking University-Tuizhan AIGC Joint Laboratory, the project currently has limited resources and seeks contributions from the open-source community. The project provides training code and welcomes Pull Requests.

Reproduce Sora model
Build knowledge about Video-VQVAE and DiT
Open-source community collaboration

Video generation
machine learning research
AI model development

Researchers use Open-Sora-Plan to reproduce the Sora model for video generation research.
Developers train their own Video-VQVAE models using the code provided by the project.
Students utilize this project to learn how to use DiT for video processing.

Visit

Open-Sora-Plan Visit Over Time

Monthly Visits

494758773

Bounce Rate

37.69%

Page per Visit

5.7

Visit Duration

00:06:29

Open-Sora-Plan Visit Trend

Open-Sora-Plan Visit Geography

Open-Sora-Plan Traffic Sources

Open-Sora-Plan Alternatives

Ruyi-Mini-7B — Open-source image to video generation model

Video•Image to Video•Video Generation

CausVid — A fast causal video generator that enables instant video generation.

Video•Video Generation•Artificial Intelligence

150

HunyuanVideo — A large-scale video generation model training framework open-sourced by Tencent.

Video•Video Generation•Artificial Intelligence

312

SoraVids — Archive library for the video generation model Sora.

Video•Video Generation•Machine Learning

LTX-Video — A video generation model based on DiT, capable of real-time high-quality video generation.

Video•Video Generation•Artificial Intelligence

258

Mira — An experimental framework designed for high-quality long video generation, featuring extended sequence lengths and enhanced dynamic properties.

Video•Video Generation•Text-to-Video

780

GenAI Courses — AI Learning Platform

Education•AI learning•Machine learning

528

Ruyi-Models — An image-to-video model capable of producing cinematic-quality videos

Image•Image-to-video•Video generation

INFP — An audio-driven interactive head generation framework designed for two-person conversations.

Video•Audio-Driven•Interactive

PromptWizard — Task-aware prompt optimization framework

Programming•Microsoft•LLM

240

AI Kissing Video Generator — Transforms photos into realistic kissing videos using AI technology.

Video•AI Technology•Video Generation

132

Gemini 2.0 Flash Thinking — An AI model developed by Google, offering responses with enhanced reasoning capabilities.

InternationalSelection•Machine Learning•Reasoning

366

Gemini 2.0 Flash Experimental — A high-performance AI model developed by Google DeepMind

InternationalSelection•Machine Learning•Natural Language Processing

162

Ruyi — A large model that generates videos from images, specifically designed for anime and game scenes.

Video•AIGC•Video Generation

Astris AI — Astris AI is a division launched by Lockheed Martin that focuses on secure artificial intelligence solutions.

Others•Artificial Intelligence•Machine Learning

FastHunyuan — Model for rapid high-quality video generation

Video•Video Generation•AI Model

Phi Open Models — Phi Open Models are powerful, cost-effective, low-latency small language models.

Productivity•Machine Learning•Small Language Models

Recursal AI — Making artificial intelligence accessible

Productivity•Artificial Intelligence•Machine Learning

Apollo-LMMs — Exploration of Video Understanding in Large Multimodal Models

Video•Video Understanding•Multimodal Models

ComfyUI-HunyuanVideoWrapper-IP2V — A video generation tool based on HunyuanVideo that supports image-to-video conversion.

Video•Video Generation•Image to Video

126

RWKV-6 Mixture of Experts — The largest model in the RWKV family, utilizing MoE technology to enhance efficiency.

Programming•Machine Learning•MoE

Veo 2 — An advanced video generation model from Google DeepMind

InternationalSelection•Video Generation•DeepMind

342

Q-RWKV-6 32B Instruct Preview — The most powerful variant of the RWKV model, breaking multiple English benchmark tests.

Programming•Machine Learning•Natural Language Processing

Best AI Websites & Tools

Open-Sora-Plan

Open-Sora-Plan Visit Over Time

Open-Sora-Plan Visit Trend

Open-Sora-Plan Visit Geography

Open-Sora-Plan Traffic Sources

Open-Sora-Plan Alternatives

Ruyi-Mini-7B — Open-source image to video generation model

CausVid — A fast causal video generator that enables instant video generation.

HunyuanVideo — A large-scale video generation model training framework open-sourced by Tencent.

SoraVids — Archive library for the video generation model Sora.

LTX-Video — A video generation model based on DiT, capable of real-time high-quality video generation.

genmoai — Open-source video generation model

Movie Gen Bench — Video Generation Evaluation Benchmark

DeepMind — A leading artificial intelligence research company under Google

ControlNeXt — Controllable video and image generation technology

VideoTetris — An innovative framework for text-to-video generation

Pandora — General world model, supports natural language action and video state

Mira — An experimental framework designed for high-quality long video generation, featuring extended sequence lengths and enhanced dynamic properties.

GenAI Courses — AI Learning Platform

Ruyi-Models — An image-to-video model capable of producing cinematic-quality videos

INFP — An audio-driven interactive head generation framework designed for two-person conversations.

PromptWizard — Task-aware prompt optimization framework

AI Kissing Video Generator — Transforms photos into realistic kissing videos using AI technology.

Gemini 2.0 Flash Thinking — An AI model developed by Google, offering responses with enhanced reasoning capabilities.

Gemini 2.0 Flash Experimental — A high-performance AI model developed by Google DeepMind

Ruyi — A large model that generates videos from images, specifically designed for anime and game scenes.

Astris AI — Astris AI is a division launched by Lockheed Martin that focuses on secure artificial intelligence solutions.

FastHunyuan — Model for rapid high-quality video generation

Phi Open Models — Phi Open Models are powerful, cost-effective, low-latency small language models.

Recursal AI — Making artificial intelligence accessible

Apollo-LMMs — Exploration of Video Understanding in Large Multimodal Models

ComfyUI-HunyuanVideoWrapper-IP2V — A video generation tool based on HunyuanVideo that supports image-to-video conversion.

RWKV-6 Mixture of Experts — The largest model in the RWKV family, utilizing MoE technology to enhance efficiency.

Veo 2 — An advanced video generation model from Google DeepMind

Q-RWKV-6 32B Instruct Preview — The most powerful variant of the RWKV model, breaking multiple English benchmark tests.