Open-Sora-Plan

Open-Sora Plan This project aims to create a simple and scalable repo, to reproduce Sora (OpenAI, but we prefer to call it "ClosedAI"). This project aims to reproduce Sora through the power of the open source community, jointly initiated by the North University-Rabbit AIGC Laboratory, with deep contributions from Rabbit, Huawei, Pengcheng Laboratory, and open source community partners. The current V1.5 version is fully based on Huawei Ascend training (Ascend pure blood version), and is welcome to Pull Request and use! We are rapidly iterating new versions, and welcome more contributors or algorithm engineers to join us. Algorithm Engineer Recruitment-Rabbit Intelligence.pdf If you like our project, please give us a star ⭐ on GitHub for the latest update. News [2026.03.08] We introduce Helios, a breakthrough video generation model that achieves minute-scale, high-quality video synthesis at 19.5 FPS on a single H100 GPU — without relying on conventional long video anti-drifting strategies or standard video acceleration techniques. Welcome to check the Technical Report! [2025.06.05] We release version 1.5.0, our most powerful model! By introducing a higher-compression WFVAE and an improved sparse DiT architecture, SUV, we achieve performance comparable to HunyuanVideo (Open-Source) using an 8B-scale model and 40 million video samples. Version 1.5.0 is fully trained and inferred on Ascend 910-series accelerators; please check the mindspeedmmdit branch for our new code and Report-v1.5.0.md for our report. The GPU version is coming soon. [2024.12.03] ⚡️ We released our arxiv paper and WF-VAE paper for v1.3. The next more powerful version is coming soon. [2024.10.16] We released version 1.3.0, featuring: WFVAE, prompt refiner, data filtering strategy, sparse attention, and bucket training strategy. We also support 93x480p within 24G VRAM. More details can be found at our latest report. [2024.08.13] We are launching Open-Sora Plan v1.2.0 I2V model, which is based on Open-Sora Plan v1.2.0. The current version supports image-to-video generation and transition generation (the starting and ending frames conditions for video generation). Check out the Image-to-Video section in this report. [2024.07.24] v1.2.0 is here! Utilizing a 3D full attention architecture instead of 2+1D. We released a true 3D video diffusion model trained on 4s 720p. Check out our latest report. [2024.05.27] We are launching Open-Sora Plan v1.1.0, which significantly improves video quality and length, and is fully 开源! Please check out our latest report. Tha…