# Open-Sora Plan
<!--
[[Project Page]](https://pku-yuangroup.github.io/Open-Sora-Plan/) [[ä¸æ主页]](https://pku-yuangroup.github.io/Open-Sora-Plan/blog_cn.html)
-->
[![slack badge](https://img.shields.io/badge/Discord-join-blueviolet?logo=discord&)](https://discord.gg/vqGmpjkSaz)
[![WeChat badge](https://img.shields.io/badge/微信-å å
¥-green?logo=wechat&)](https://github.com/PKU-YuanGroup/Open-Sora-Plan/issues/53#issuecomment-1987226516)
[![Twitter](https://img.shields.io/badge/-Twitter@LinBin46984-black?logo=twitter&logoColor=1D9BF0)](https://x.com/LinBin46984/status/1763476690385424554?s=20) <br>
[![hf_space](https://img.shields.io/badge/ð¤-Open%20In%20Spaces-blue.svg)](https://huggingface.co/spaces/LanguageBind/Open-Sora-Plan-v1.0.0)
[![hf_space](https://img.shields.io/badge/ð¤-Open%20In%20Spaces-blue.svg)](https://huggingface.co/spaces/fffiloni/Open-Sora-Plan-v1-0-0)
[![Replicate demo and cloud API](https://replicate.com/camenduru/open-sora-plan-512x512/badge)](https://replicate.com/camenduru/open-sora-plan-512x512)
[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/camenduru/Open-Sora-Plan-jupyter/blob/main/Open_Sora_Plan_jupyter.ipynb) <br>
[![License](https://img.shields.io/badge/License-MIT-yellow)](https://github.com/PKU-YuanGroup/Open-Sora-Plan/blob/main/LICENSE)
[![GitHub repo contributors](https://img.shields.io/github/contributors-anon/PKU-YuanGroup/Open-Sora-Plan?style=flat&label=Contributors)](https://github.com/PKU-YuanGroup/Open-Sora-Plan/graphs/contributors)
[![GitHub Commit](https://img.shields.io/github/commit-activity/m/PKU-YuanGroup/Open-Sora-Plan?label=Commit)](https://github.com/PKU-YuanGroup/Open-Sora-Plan/commits/main/)
[![Pr](https://img.shields.io/github/issues-pr-closed-raw/PKU-YuanGroup/Open-Sora-Plan.svg?label=Merged+PRs&color=green)](https://github.com/PKU-YuanGroup/Open-Sora-Plan/pulls)
[![GitHub issues](https://img.shields.io/github/issues/PKU-YuanGroup/Open-Sora-Plan?color=critical&label=Issues)](https://github.com/PKU-YuanGroup/Video-LLaVA/issues?q=is%3Aopen+is%3Aissue)
[![GitHub closed issues](https://img.shields.io/github/issues-closed/PKU-YuanGroup/Open-Sora-Plan?color=success&label=Issues)](https://github.com/PKU-YuanGroup/Video-LLaVA/issues?q=is%3Aissue+is%3Aclosed) <br>
[![GitHub repo stars](https://img.shields.io/github/stars/PKU-YuanGroup/Open-Sora-Plan?style=flat&logo=github&logoColor=whitesmoke&label=Stars)](https://github.com/PKU-YuanGroup/Open-Sora-Plan/stargazers) 
[![GitHub repo forks](https://img.shields.io/github/forks/PKU-YuanGroup/Open-Sora-Plan?style=flat&logo=github&logoColor=whitesmoke&label=Forks)](https://github.com/PKU-YuanGroup/Open-Sora-Plan/network) 
[![GitHub repo watchers](https://img.shields.io/github/watchers/PKU-YuanGroup/Open-Sora-Plan?style=flat&logo=github&logoColor=whitesmoke&label=Watchers)](https://github.com/PKU-YuanGroup/Open-Sora-Plan/watchers) 
[![GitHub repo size](https://img.shields.io/github/repo-size/PKU-YuanGroup/Open-Sora-Plan?style=flat&logo=github&logoColor=whitesmoke&label=Repo%20Size)](https://github.com/PKU-YuanGroup/Open-Sora-Plan/archive/refs/heads/main.zip)
We are thrilled to present **Open-Sora-Plan v1.0.0**, which significantly enhances video generation quality and text control capabilities. See our [report](docs/Report-v1.0.0.md). We are training for higher resolution (>1024) as well as longer duration (>10s) videos, here is a preview of the next release. We show compressed .gif on github, which loses some quality.
Thanks to **HUAWEI Ascend NPU Team** for supporting us.
ç®åå·²æ¯æå½äº§AIè¯ç(å为æè
¾910ï¼æå¾
æ´å¤å½äº§ç®åè¯ç)è¿è¡æ¨çï¼ä¸ä¸æ¥å°æ¯æå½äº§ç®åè®ç»ï¼å
·ä½å¯åèæè
¾åæ¯[hw branch](https://github.com/PKU-YuanGroup/Open-Sora-Plan/tree/hw).
| 257Ã512Ã512 (10s) | 65Ã1024Ã1024 (2.7s) | 65Ã1024Ã1024 (2.7s) |
| --- | --- | --- |
| <img src="https://github.com/PKU-YuanGroup/Open-Sora-Plan/assets/88202804/37c29fcb-47ba-4c6e-9ce8-612f0eab6634" width=224> | <img src="https://github.com/PKU-YuanGroup/Open-Sora-Plan/assets/88202804/6362c3ad-b1c4-4c36-8737-ad8a1e1dbed4" width=448> |<img src="https://github.com/PKU-YuanGroup/Open-Sora-Plan/assets/88202804/d90dd228-611b-44b7-93f4-fa99e224bd11" width=448> |
| Time-lapse of a coastal landscape transitioning from sunrise to nightfall... | A quiet beach at dawn, the waves gently lapping at the shore and the sky painted in pastel hues....|Sunset over the sea. |
| 65Ã512Ã512 (2.7s) | 65Ã512Ã512 (2.7s) | 65Ã512Ã512 (2.7s) |
| --- | --- | --- |
| <img src="https://github.com/PKU-YuanGroup/Open-Sora-Plan/assets/88202804/deca421b-dbc5-4d16-a80b-89c1d8b4fce7" width=224> | <img src="https://github.com/PKU-YuanGroup/Open-Sora-Plan/assets/88202804/7cddd996-7c17-4d8e-a47d-e57c0930a91d" width=224> | <img src="https://github.com/PKU-YuanGroup/Open-Sora-Plan/assets/88202804/029ed424-e977-470b-a39d-ebc2d3e61c1c" width=224> |
| A serene underwater scene featuring a sea turtle swimming... | Yellow and black tropical fish dart through the sea. | a dynamic interaction between the ocean and a large rock... |
| <img src="https://github.com/PKU-YuanGroup/Open-Sora-Plan/assets/88202804/900e7293-9c7c-4844-b7e7-c0b0b9f7e055" width=224> | <img src="https://github.com/PKU-YuanGroup/Open-Sora-Plan/assets/88202804/a710d498-5f43-4553-be12-e80f9d5b442e" width=224> | <img src="https://github.com/PKU-YuanGroup/Open-Sora-Plan/assets/88202804/1d350503-98f6-4e88-8802-2dd915357726" width=224> |
| The dynamic movement of tall, wispy grasses swaying in the wind... | Slow pan upward of blazing oak fire in an indoor fireplace. | A serene waterfall cascading down moss-covered rocks... |
## ðª Goal
This project aims to create a simple and scalable repo, to reproduce [Sora](https://openai.com/sora) (OpenAI, but we prefer to call it "ClosedAI" ). We wish the open-source community can contribute to this project. Pull requests are welcome!!!
æ¬é¡¹ç®å¸æéè¿å¼æºç¤¾åºçåéå¤ç°Soraï¼ç±å大-å
å±AIGCèåå®éªå®¤å
±ååèµ·ï¼å½åçæ¬ç¦»ç®æ å·®è·ä»ç¶è¾å¤§ï¼ä»éæç»å®ååå¿«éè¿ä»£ï¼æ¬¢è¿Pull requestï¼ï¼ï¼
Project stages:
- Primary
1. Setup the codebase and train a un-conditional model on a landscape dataset.
2. Train models that boost resolution and duration.
- Extensions
3. Conduct text2video experiments on landscape dataset.
4. Train the 1080p model on video2text dataset.
5. Control model with more conditions.
<div style="display: flex; justify-content: center;">
<img src="https://github.com/PKU-YuanGroup/Open-Sora-Plan/assets/88202804/6b3095e9-88e8-4481-9b1b-ff9aaa25caf1" width=200>
<img src="https://github.com/PKU-YuanGroup/Open-Sora-Plan/assets/88202804/f0a2ebca-6d25-4f94-be29-bd0a29cd9230" width=600>
</div>
## ð° News
**[2024.04.09]** ð Excited to share our latest exploration on metamorphic time-lapse video generation: [MagicTime](https://github.com/PKU-YuanGroup/MagicTime), which learns real-world physics knowledge from time-lapse videos. Here is the dataset for train (updating): [Open-Sora-Dataset](https://github.com/PKU-YuanGroup/Open-Sora-Dataset).
**[2024.04.07]** ð¥ð¥ð¥ Today, we are thrilled to present Open-Sora-Plan v1.0.0, which significantly enhances video generation quality and text control capabilities. See our [report](docs/Report-v1.0.0.md). Thanks to HUAWEI NPU for supporting us.
**[2024.03.27]** ððð We release the report of [VideoCausalVAE](docs/CausalVideoVAE.md), which supports both images and videos. We present our reconstructed video in this demonstration as follows. The text-to-video model is on the way.
**[2024.03.10]** ððð This repo supports training a latent size of 225Ã90Ã90 (tÃhÃw), which means we are able to **train 1 minute of 1080P video with 30FPS** (2Ã interpolated frames and 2Ã super resolution) under class-condition.
**[2024.03.08]** We
没有合适的资源?快使用搜索试试~ 我知道了~
本项目旨在重现 Sora(Open AI T2V 模型)们希望开源社区为本项目做出贡献
共228个文件
py:155个
sh:28个
md:12个
1.该资源内容由用户上传,如若侵权请联系客服进行举报
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
版权申诉
0 下载量 161 浏览量
2024-04-10
17:42:24
上传
评论
收藏 540KB ZIP 举报
温馨提示
Open-Sora-Plan v1.0.0,它显着增强了视频生成质量和文本控制功能。请参阅我们的报告。我们正在训练更高分辨率 (>1024) 以及更长持续时间 (>10s) 的视频,这里是下一个版本的预览。我们在 github 上显示压缩.gif,这会损失一些质量。前已支持国产AI芯片(华为昇腾910,期待更多国产算力芯片)进行推理,下一步将支持国产算力训练,具体可参考昇腾分支hw branch。目前已支持国产AI芯片(华为昇腾910,期待更多国产算力芯片)进行推理,下一步将支持国产算力训练,具体可参考昇腾分支hw branch。该项目旨在创建一个简单且可扩展的存储库,以重现 Sora(OpenAI,但我们更愿意将其称为“ClosedAI”)。我们希望开源社区能够为这个项目做出贡献。欢迎拉取请求。设置代码库并在景观数据集上训练无条件模型。在景观数据集上进行text2video实验。在 video2text 数据集上训练 1080p 模型。具有更多条件的控制模型。
资源推荐
资源详情
资源评论
收起资源包目录
本项目旨在重现 Sora(Open AI T2V 模型)们希望开源社区为本项目做出贡献 (228个子文件)
dockerfile.base 891B
curope.cpp 2KB
kernels.cu 4KB
.gitignore 157B
hostfile 68B
release.json 1KB
zero3_offload.json 955B
zero3.json 798B
zero2_offload.json 648B
zero2.json 553B
captions.json 173B
LICENSE 1KB
LICENSE 1KB
README.md 23KB
Report-v1.0.0.md 13KB
Report-v1.0.0-cn.md 11KB
Train_And_Eval_CausalVideoVAE.md 7KB
EVAL.md 4KB
Contribution_Guidelines.md 3KB
README.md 2KB
VQVAE.md 2KB
Data.md 1KB
README.md 1KB
readme.md 1KB
README.md 973B
placeholder 0B
run_docker.png 86KB
build_docker.png 63KB
modules.py 73KB
modeling_latte.py 61KB
train_t2v_t5_feature.py 38KB
train_t2v.py 37KB
train_t2v_feature.py 36KB
gaussian_diffusion_t2v.py 36KB
pipeline_videogen.py 35KB
train.py 35KB
gaussian_diffusion.py 34KB
modeling_causalvqvae.py 30KB
model.py 30KB
rgt_arch.py 28KB
modeling_vqvae.py 27KB
modeling_causalvae.py 22KB
quantize.py 18KB
losses.py 18KB
vqgan.py 17KB
utils.py 16KB
perceptual_loss.py 16KB
pwcnet.py 15KB
transform.py 15KB
base_model.py 15KB
transport.py 14KB
correlation.py 14KB
matlab_functions.py 14KB
pytorch_i3d.py 13KB
flolpips.py 13KB
arch_util.py 11KB
feat_enc.py 11KB
data_util.py 10KB
feature_datasets.py 9KB
rec_video_vae.py 9KB
sr_model.py 9KB
eval_common_metric.py 9KB
clip.py 8KB
t5.py 8KB
utils.py 8KB
eval_clip_score.py 8KB
respace.py 8KB
raft.py 8KB
AMT-G.py 8KB
transport_sample.py 8KB
sample_t2v.py 8KB
attention.py 8KB
updownsample.py 7KB
gradio_utils.py 7KB
logger.py 7KB
path.py 7KB
options.py 7KB
pretrained_networks.py 7KB
interpolation.py 6KB
transforms.py 6KB
img_util.py 6KB
vgg_arch.py 6KB
file_client.py 6KB
timestep_sampler.py 6KB
pos.py 6KB
rgt_model.py 6KB
rec_imvi_vae.py 5KB
caption_refiner.py 5KB
pos_embed.py 5KB
fvd.py 5KB
sample.py 5KB
run.py 5KB
paired_image_dataset.py 5KB
gradio_web_server.py 5KB
sky_datasets.py 5KB
train_causalvae.py 5KB
lpips.py 5KB
discriminator.py 5KB
misc.py 5KB
t2v_datasets.py 5KB
共 228 条
- 1
- 2
- 3
资源评论
传奇开心果编程
- 粉丝: 8459
- 资源: 335
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功