/Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

Primary LanguagePythonApache License 2.0Apache-2.0

Open-Sora: Democratizing Efficient Video Production for All

We present Open-Sora, an initiative dedicated to efficiently produce high-quality video and make the model, tools and contents accessible to all. By embracing open-source principles, Open-Sora not only democratizes access to advanced video generation techniques, but also offers a streamlined and user-friendly platform that simplifies the complexities of video production. With Open-Sora, we aim to inspire innovation, creativity, and inclusivity in the realm of content creation.

[中文文档]

Open-Sora is still at an early stage and under active development.

📰 News

  • [2024.03.18] 🔥 We release Open-Sora 1.0, a fully open-source project for video generation. Open-Sora 1.0 supports a full pipeline of video data preprocessing, training with acceleration, inference, and more. Our provided checkpoints can produce 2s 512x512 videos with only 3 days training. [blog]
  • [2024.03.04] Open-Sora provides training with 46% cost reduction. [blog]

🎥 Latest Demo

2s 512×512 2s 512×512 2s 512×512
A serene night scene in a forested area. [...] The video is a time-lapse, capturing the transition from day to night, with the lake and forest serving as a constant backdrop. A soaring drone footage captures the majestic beauty of a coastal cliff, [...] The water gently laps at the rock base and the greenery that clings to the top of the cliff. The majestic beauty of a waterfall cascading down a cliff into a serene lake. [...] The camera angle provides a bird's eye view of the waterfall.
A bustling city street at night, filled with the glow of car headlights and the ambient light of streetlights. [...] The vibrant beauty of a sunflower field. The sunflowers are arranged in neat rows, creating a sense of order and symmetry. [...] A serene underwater scene featuring a sea turtle swimming through a coral reef. The turtle, with its greenish-brown shell [...]

Videos are downsampled to .gif for display. Click for original videos. Prompts are trimmed for display, see here for full prompts. See more samples at our gallery.

🔆 New Features/Updates

  • 📍 Open-Sora-v1 released. Model weights are available here. With only 400K video clips and 200 H800 days (compared with 152M samples in Stable Video Diffusion), we are able to generate 2s 512×512 videos.
  • ✅ Three stages training from an image diffusion model to a video diffusion model. We provide the weights for each stage.
  • ✅ Support training acceleration including accelerated transformer, faster T5 and VAE, and sequence parallelism. Open-Sora improve 55% training speed when training on 64x512x512 videos. Details locates at acceleration.md.
  • ✅ We provide data preprocessing pipeline, including downloading, video cutting, and captioning tools. Our data collection plan can be found at datasets.md.
  • ✅ We find VQ-VAE from VideoGPT has a low quality and thus adopt a better VAE from Stability-AI. We also find patching in the time dimension deteriorates the quality. See our report for more discussions.
  • ✅ We investigate different architectures including DiT, Latte, and our proposed STDiT. Our STDiT achieves a better trade-off between quality and speed. See our report for more discussions.
  • ✅ Support clip and T5 text conditioning.
  • ✅ By viewing images as one-frame videos, our project supports training DiT on both images and videos (e.g., ImageNet & UCF101). See commands.md for more instructions.
  • ✅ Support inference with official weights from DiT, Latte, and PixArt.
View more
  • ✅ Refactor the codebase. See structure.md to learn the project structure and how to use the config files.

TODO list sorted by priority

  • Complete the data processing pipeline (including dense optical flow, aesthetics scores, text-image similarity, deduplication, etc.). See datasets.md for more information. [WIP]
  • Training Video-VAE. [WIP]
View more
  • Support image and video conditioning.
  • Evaluation pipeline.
  • Incoporate a better scheduler, e.g., rectified flow in SD3.
  • Support variable aspect ratios, resolutions, durations.
  • Support SD3 when released.

Contents

Installation

# create a virtual env
conda create -n opensora python=3.10
# activate virtual environment
conda activate opensora

# install torch
# the command below is for CUDA 12.1, choose install commands from
# https://pytorch.org/get-started/locally/ based on your own CUDA version
pip install torch torchvision

# install flash attention (optional)
# set enable_flashattn=False in config to avoid using flash attention
pip install packaging ninja
pip install flash-attn --no-build-isolation

# install apex (optional)
# set enable_layernorm_kernel=False in config to avoid using apex
pip install -v --disable-pip-version-check --no-cache-dir --no-build-isolation --config-settings "--build-option=--cpp_ext" --config-settings "--build-option=--cuda_ext" git+https://github.com/NVIDIA/apex.git

# install xformers
pip install -U xformers --index-url https://download.pytorch.org/whl/cu121

# install this project
git clone https://github.com/hpcaitech/Open-Sora
cd Open-Sora
pip install -v .

After installation, we suggest reading structure.md to learn the project structure and how to use the config files.

Model Weights

Resolution Data #iterations Batch Size GPU days (H800) URL
16×512×512 20K HQ 20k 2×64 35 🔗
16×256×256 20K HQ 24k 8×64 45 🔗
16×256×256 366K 80k 8×64 117 🔗

Training orders: 16x256x256 $\rightarrow$ 16x256x256 HQ $\rightarrow$ 16x512x512 HQ.

Our model's weight is partially initialized from PixArt-α. The number of parameters is 724M. More information about training can be found in our report. More about the dataset can be found in datasets.md. HQ means high quality.

⚠️ LIMITATION: Our model is trained on a limited budget. The quality and text alignment is relatively poor. The model performs badly, especially on generating human beings and cannot follow detailed instructions. We are working on improving the quality and text alignment.

Inference

We have provided a Gradio application in this repository, you can use the following the command to start an interactive web application to experience video generation with Open-Sora.

pip install gradio spaces
python gradio/app.py

This will launch a Gradio application on your localhost. If you want to know more about the Gradio applicaiton, you can refer to the README file.

Besides, we have also provided an offline inference script. Run the following commands to generate samples, the required model weights will be automatically downloaded. To change sampling prompts, modify the txt file passed to --prompt-path. See here to customize the configuration.

# Sample 16x512x512 (20s/sample, 100 time steps, 24 GB memory)
torchrun --standalone --nproc_per_node 1 scripts/inference.py configs/opensora/inference/16x512x512.py --ckpt-path OpenSora-v1-HQ-16x512x512.pth --prompt-path ./assets/texts/t2v_samples.txt

# Sample 16x256x256 (5s/sample, 100 time steps, 22 GB memory)
torchrun --standalone --nproc_per_node 1 scripts/inference.py configs/opensora/inference/16x256x256.py --ckpt-path OpenSora-v1-HQ-16x256x256.pth --prompt-path ./assets/texts/t2v_samples.txt

# Sample 64x512x512 (40s/sample, 100 time steps)
torchrun --standalone --nproc_per_node 1 scripts/inference.py configs/opensora/inference/64x512x512.py --ckpt-path ./path/to/your/ckpt.pth --prompt-path ./assets/texts/t2v_samples.txt

# Sample 64x512x512 with sequence parallelism (30s/sample, 100 time steps)
# sequence parallelism is enabled automatically when nproc_per_node is larger than 1
torchrun --standalone --nproc_per_node 2 scripts/inference.py configs/opensora/inference/64x512x512.py --ckpt-path ./path/to/your/ckpt.pth --prompt-path ./assets/texts/t2v_samples.txt

The speed is tested on H800 GPUs. For inference with other models, see here for more instructions. To lower the memory usage, set a smaller vae.micro_batch_size in the config (slightly lower sampling speed).

Data Processing

High-quality Data is the key to high-quality models. Our used datasets and data collection plan is here. We provide tools to process video data. Currently, our data processing pipeline includes the following steps:

  1. Downloading datasets. [docs]
  2. Split videos into clips. [docs]
  3. Generate video captions. [docs]

Training

To launch training, first download T5 weights into pretrained_models/t5_ckpts/t5-v1_1-xxl. Then run the following commands to launch training on a single node.

# 1 GPU, 16x256x256
torchrun --nnodes=1 --nproc_per_node=1 scripts/train.py configs/opensora/train/16x256x256.py --data-path YOUR_CSV_PATH
# 8 GPUs, 64x512x512
torchrun --nnodes=1 --nproc_per_node=8 scripts/train.py configs/opensora/train/64x512x512.py --data-path YOUR_CSV_PATH --ckpt-path YOUR_PRETRAINED_CKPT

To launch training on multiple nodes, prepare a hostfile according to ColossalAI, and run the following commands.

colossalai run --nproc_per_node 8 --hostfile hostfile scripts/train.py configs/opensora/train/64x512x512.py --data-path YOUR_CSV_PATH --ckpt-path YOUR_PRETRAINED_CKPT

For training other models and advanced usage, see here for more instructions.

Contribution

Thanks goes to these wonderful contributors (emoji key following all-contributors specification):

zhengzangw
zhengzangw
💻 📖 🤔 📹 🚧		 ver217
ver217
💻 🤔 📖 🐛		 FrankLeeeee
FrankLeeeee
💻 🚇 🔧		 xyupeng
xyupeng
💻 📖 🎨		 Yanjia0
Yanjia0
📖
binmakeswell
binmakeswell
📖		 eltociear
eltociear
📖		 ganeshkrishnan1
ganeshkrishnan1
📖		 fastalgo
fastalgo
📖		 powerzbt
powerzbt
📖

If you wish to contribute to this project, you can refer to the Contribution Guideline.

Acknowledgement

  • ColossalAI: A powerful large model parallel acceleration and optimization system.
  • DiT: Scalable Diffusion Models with Transformers.
  • OpenDiT: An acceleration for DiT training. We adopt valuable acceleration strategies for training progress from OpenDiT.
  • PixArt: An open-source DiT-based text-to-image model.
  • Latte: An attempt to efficiently train DiT for video.
  • StabilityAI VAE: A powerful image VAE model.
  • CLIP: A powerful text-image embedding model.
  • T5: A powerful text encoder.
  • LLaVA: A powerful image captioning model based on Yi-34B.

We are grateful for their exceptional work and generous contribution to open source.

Citation

@software{opensora,
  author = {Zangwei Zheng and Xiangyu Peng and Yang You},
  title = {Open-Sora: Democratizing Efficient Video Production for All},
  month = {March},
  year = {2024},
  url = {https://github.com/hpcaitech/Open-Sora}
}

Zangwei Zheng and Xiangyu Peng equally contributed to this work during their internship at HPC-AI Tech.

Star History

Star History Chart