- **[2024.06.17]** 🔥 We released **Open-Sora 1.2**, which includes **3D-VAE**, **rectified flow**, and **score condition**. The video quality is greatly improved. [[checkpoints]](#open-sora-10-model-weights) [[report]](/docs/report_03.md) [[blog]](https://hpc-ai.com/blog/open-sora-from-hpc-ai-tech-team-continues-open-source-generate-any-16-second-720p-hd-video-with-one-click-model-weights-ready-to-use)
- **[2024.04.25]** 🤗 We released the [Gradio demo for Open-Sora](https://huggingface.co/spaces/hpcai-tech/open-sora) on Hugging Face Spaces.
- **[2024.04.25]** We released **Open-Sora 1.1**, which supports **2s~15s, 144p to 720p, any aspect ratio** text-to-image, **text-to-video, image-to-video, video-to-video, infinite time** generation. In addition, a full video processing pipeline is released. [[checkpoints]]() [[report]](/docs/report_02.md)
- **[2024.03.18]** We released **Open-Sora 1.0**, a fully open-source project for video generation.
🔥 You can experience Open-Sora on our [🤗 Gradio application on Hugging Face](https://huggingface.co/spaces/hpcai-tech/open-sora). More samples and corresponding prompts are available in our [Gallery](https://hpcaitech.github.io/Open-Sora/).
| 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 [...] |
- ✅ Support more conditioning including fps, aesthetic score, motion strength and camera motion.
- ✅ Trained our 3D-VAE for temporal dimension compression.
- 📍 **Open-Sora 1.1** released. Model weights are available [here](#model-weights). It is trained on **0s~15s, 144p to 720p, various aspect ratios** videos. See our **[report 1.1](/docs/report_02.md)** for more discussions.
- 🔧 **Data processing pipeline v1.1** is released. An automatic [processing pipeline](#data-processing) from raw videos to (text, video clip) pairs is provided, including scene cutting $\rightarrow$ filtering(aesthetic, optical flow, OCR, etc.) $\rightarrow$ captioning $\rightarrow$ managing. With this tool, you can easily build your video dataset.
days (compared with 152M samples in Stable Video Diffusion), we are able to generate 2s 512×512 videos. See our **[report 1.0](docs/report_01.md)** for more discussions.
- [x] Training Video-VAE and adapt our model to new VAE.
- [x] Scaling model parameters and dataset size.
- [x] Incoporate a better scheduler (rectified flow).
- [x] Evaluation pipeline.
- [x] Complete the data processing pipeline (including dense optical flow, aesthetics scores, text-image similarity, etc.). See [the dataset](/docs/datasets.md) for more information
- [x] Support image and video conditioning.
- [x] Support variable aspect ratios, resolutions, durations.
- Report: each version is trained from a image base seperately (not continuously trained), while a newer version will incorporate the techniques from the previous version.
- [report 1.2](docs/report_03.md): rectified flow, 3d-VAE, score condition, evaluation, etc.
- [report 1.1](docs/report_02.md): multi-resolution/length/aspect-ratio, image/video conditioning/editing, data preprocessing, etc.
- [report 1.0](docs/report_01.md): architecture, captioning, etc.
- Data processing pipeline and dataset: [datasets.md](docs/datasets.md)
- Each data processing tool's README: [dataset conventions and management](/tools/datasets/README.md), [scene cutting](/tools/scene_cut/README.md), [scoring](/tools/scoring/README.md), [caption](/tools/caption/README.md)
For CUDA 12.1, you can install the dependencies with the following commands. Otherwise, please refer to [Installation Documentation](docs/installation.md) for more instructions on different cuda version, and additional dependency for data preprocessing, VAE, and model evaluation.
(Optional, recommended for fast speed, especially for training) To enable `layernorm_kernel` and `flash_attn`, you need to install `apex` and `flash-attn` with the following commands.
```bash
# install flash attention
# set enable_flash_attn=False in config to disable flash attention
pip install packaging ninja
pip install flash-attn --no-build-isolation
# install apex
# set enable_layernorm_kernel=False in config to disable apex
See our **[report 1.1](docs/report_02.md)** for more infomation.
:warning: **LIMITATION**: This version contains known issues which we are going to fix in the next version (as we save computation resource for the next release). In addition, the video generation may fail for long duration, and high resolution will have noisy results due to this problem.
If you want to deploy gradio locally, we have also provided a [Gradio application](./gradio) in this repository, you can use the following the command to start an interactive web application to experience video generation with Open-Sora.
This will launch a Gradio application on your localhost. If you want to know more about the Gradio applicaiton, you can refer to the [Gradio README](./gradio/README.md).
To enable prompt enhancement and other language input (e.g., 中文输入), you need to set the `OPENAI_API_KEY` in the environment. Check [OpenAI's documentation](https://platform.openai.com/docs/quickstart) to get your API key.
```bash
export OPENAI_API_KEY=YOUR_API_KEY
```
### Getting Started
In the Gradio application, the basic options are as follows:
The easiest way to generate a video is to input a text prompt and click the "**Generate video**" button (scroll down if you cannot find). The generated video will be displayed in the right panel. Checking the "**Enhance prompt with GPT4o**" will use GPT-4o to refine the prompt, while "**Random Prompt**" button will generate a random prompt by GPT-4o for you. Due to the OpenAI's API limit, the prompt refinement result has some randomness.
Then, you can choose the **resolution**, **duration**, and **aspect ratio** of the generated video. Different resolution and video length will affect the video generation speed. On a 80G H100 GPU, the generation speed (with `num_sampling_step=30`) and peak memory usage is:
Note that besides text to video, you can also use **image to video generation**. You can upload an image and then click the "**Generate video**" button to generate a video with the image as the first frame. Or you can fill in the text prompt and click the "**Generate image**" button to generate an image with the text prompt, and then click the "**Generate video**" button to generate a video with the image generated with the same model.
Then you can specify more options, including "**Motion Strength**", "**Aesthetic**" and "**Camera Motion**". If "Enable" not checked or the choice is "none", the information is not passed to the model. Otherwise, the model will generate videos with the specified motion strength, aesthetic score, and camera motion.
For the **aesthetic score**, we recommend using values higher than 6. For **motion strength**, a smaller value will lead to a smoother but less dynamic video, while a larger value will lead to a more dynamic but likely more blurry video. Thus, you can try without it and then adjust it according to the generated video. For the **camera motion**, sometimes the model cannot follow the instruction well, and we are working on improving it.
You can also adjust the "**Sampling steps**", this is directly related to the generation speed as it is the number of denoising. A number smaller than 30 usually leads to a poor generation results, while a number larger than 100 usually has no significant improvement. The "**Seed**" is used for reproducibility, you can set it to a fixed number to generate the same video. The "**CFG Scale**" controls how much the model follows the text prompt, a smaller value will lead to a more random video, while a larger value will lead to a more text-following video (7 is recommended).
:warning: **LIMITATION**: The sequence parallelism is not supported for gradio deployment. For now, the sequence parallelism is only supported when the dimension can be divided by the number of GPUs. Thus, it may fail for some cases. We tested 4 GPUs for 720p and 2 GPUs for 480p.
We find that GPT-4o can refine the prompt and improve the quality of the generated video. With this feature, you can also use other language (e.g., Chinese) as the prompt. To enable this feature, you need prepare your openai api key in the environment:
Then you can inference with `--llm-refine True` to enable the GPT-4o prompt refinement, or leave prompt empty to get a random prompt generated by GPT-4o.
See [here](docs/commands.md#inference-with-open-sora-11) for more instructions including text-to-image, image-to-video, video-to-video, and infinite time generation.
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](docs/structure.md#inference-config-demos) to customize the configuration.
All the evaluation code is released in `eval` folder. Check the [README](/eval/README.md) for more details. Our [report](/docs/report_03.md#evaluation) also provides more information about the evaluation during training. The following table shows Open-Sora 1.2 greatly improves Open-Sora 1.0.
We train a VAE pipeline that consists of a spatial VAE followed by a temporal VAE.
For more details, refer to [VAE Documentation](docs/vae.md).
Before you run the following commands, follow our [Installation Documentation](docs/installation.md) to install the required dependencies for VAE and Evaluation.
If you want to train your own VAE, we need to prepare data in the csv following the [data processing](#data-processing) pipeline, then run the following commands.
Note that you need to adjust the number of trained epochs (`epochs`) in the config file accordingly with respect to your own csv data size.
- [PixArt](https://github.com/PixArt-alpha/PixArt-alpha): An open-source DiT-based text-to-image model.
- [Latte](https://github.com/Vchitect/Latte): An attempt to efficiently train DiT for video.
- [StabilityAI VAE](https://huggingface.co/stabilityai/sd-vae-ft-mse-original): A powerful image VAE model.
- [CLIP](https://github.com/openai/CLIP): A powerful text-image embedding model.
- [T5](https://github.com/google-research/text-to-text-transfer-transformer): A powerful text encoder.
- [LLaVA](https://github.com/haotian-liu/LLaVA): A powerful image captioning model based on [Mistral-7B](https://huggingface.co/mistralai/Mistral-7B-v0.1) and [Yi-34B](https://huggingface.co/01-ai/Yi-34B).
- [PLLaVA](https://github.com/magic-research/PLLaVA): A powerful video captioning model.
- [MiraData](https://github.com/mira-space/MiraData): A large-scale video dataset with long durations and structured caption.
We are grateful for their exceptional work and generous contribution to open source. Special thanks go to the authors of [MiraData](https://github.com/mira-space/MiraData) and [Rectified Flow](https://github.com/gnobitab/RectifiedFlow) for their valuable advice and help. We wish to express gratitude towards AK for sharing this project on social media and Hugging Face for providing free GPU resources for our online Gradio demo.
