You can not select more than 25 topicsTopics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
We are thrilled to present Open-Sora-Plan v1.0.0, which significantly enhances video generation quality and text control capabilities. See our report. 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.
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.
65×512×512 (2.7s)
65×512×512 (2.7s)
65×512×512 (2.7s)
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...
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...
💪 Goal
This project aims to create a simple and scalable repo, to reproduce Sora (OpenAI, but we prefer to call it "ClosedAI" ). We wish the open-source community can contribute to this project. Pull requests are welcome!!!
Setup the codebase and train a un-conditional model on a landscape dataset.
Train models that boost resolution and duration.
Extensions
Conduct text2video experiments on landscape dataset.
Train the 1080p model on video2text dataset.
Control model with more conditions.
📰 News
[2024.04.07] 🚀🚀🚀 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. Thanks to HUAWEI NPU for supporting us.
[2024.03.27] 🚀🚀🚀 We release the report of VideoCausalVAE, 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] 🚀🚀🚀 This repo supports training a latent size of 225×90×90 (t×h×w), which means we are able to train 1 minute of 1080P video with 30FPS (2× interpolated frames and 2× super resolution) under class-condition.
[2024.03.08] We support the training code of text condition with 16 frames of 512x512. The code is mainly borrowed from Latte.
[2024.03.07] We support training with 128 frames (when sample rate = 3, which is about 13 seconds) of 256x256, or 64 frames (which is about 6 seconds) of 512x512.
[2024.03.05] See our latest todo, pull requests are welcome.
[2024.03.04] We re-organizes and modulizes our code to make it easy to contribute to the project, to contribute please see the Repo structure.
[2024.03.03] We opened some discussions to clarify several issues.
[2024.03.01] Training code is available now! Learn more on our project page. Please feel free to watch 👀 this repository for the latest updates.
✊ Todo
Setup the codebase and train a unconditional model on landscape dataset
Train models that boost resolution and duration
Conduct text2video experiments on landscape dataset.
Train the 1080p model on video2text dataset
Looking for a suitable dataset, welcome to discuss and recommend. 🙏[Need your contribution]
Add synthetic video created by game engines or 3D representations. 🙏[Need your contribution]
Finish data loading, and pre-processing utils. ⌛ [WIP]
sh scripts/text_condition/train_videoae_17x256x256.sh
sh scripts/text_condition/train_videoae_65x256x256.sh
sh scripts/text_condition/train_videoae_65x512x512.sh
🚀 Improved Training Performance
In comparison to the original implementation, we implement a selection of training speed acceleration and memory saving features including gradient checkpointing, mixed precision training, and pre-extracted features, xformers, deepspeed. Some data points using a batch size of 1 with a A100:
64×32×32 (origin size: 256×256×256)
gradient checkpointing
mixed precision
xformers
feature pre-extraction
deepspeed config
compress kv
training speed
memory
✔
✔
✔
✔
❌
❌
0.64 steps/sec
43G
✔
✔
✔
✔
Zero2
❌
0.66 steps/sec
14G
✔
✔
✔
✔
Zero2
✔
0.66 steps/sec
15G
✔
✔
✔
✔
Zero2 offload
❌
0.33 steps/sec
11G
✔
✔
✔
✔
Zero2 offload
✔
0.31 steps/sec
12G
128×64×64 (origin size: 512×512×512)
gradient checkpointing
mixed precision
xformers
feature pre-extraction
deepspeed config
compress kv
training speed
memory
✔
✔
✔
✔
❌
❌
0.08 steps/sec
77G
✔
✔
✔
✔
Zero2
❌
0.08 steps/sec
41G
✔
✔
✔
✔
Zero2
✔
0.09 steps/sec
36G
✔
✔
✔
✔
Zero2 offload
❌
0.07 steps/sec
39G
✔
✔
✔
✔
Zero2 offload
✔
0.07 steps/sec
33G
💡 How to Contribute to the Open-Sora Plan Community
We greatly appreciate your contributions to the Open-Sora Plan open-source community and helping us make it even better than it is now!
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.