Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/Vchitect/Vchitect-2.0
Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models
https://github.com/Vchitect/Vchitect-2.0
Last synced: 3 months ago
JSON representation
Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models
- Host: GitHub
- URL: https://github.com/Vchitect/Vchitect-2.0
- Owner: Vchitect
- License: apache-2.0
- Created: 2024-09-09T12:18:28.000Z (3 months ago)
- Default Branch: master
- Last Pushed: 2024-09-18T15:06:13.000Z (3 months ago)
- Last Synced: 2024-09-18T15:35:48.509Z (3 months ago)
- Language: Python
- Homepage: https://vchitect.intern-ai.org.cn/
- Size: 77.5 MB
- Stars: 401
- Watchers: 6
- Forks: 10
- Open Issues: 6
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- ai-game-devtools - Vchitect-2.0 - 2.0: Parallel Transformer for Scaling Up Video Diffusion Models. | | | Video | (<span id="video">Video</span> / <span id="tool">Tool (AI LLM)</span>)
README
# Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models
1Shanghai Artificial Intelligence Laboratoryโ
๐ Join our Lark and Discord
---
[](https://hits.seeyoufarm.com)
[](https://huggingface.co/spaces/Vchitect/Vchitect-2.0)
[](https://huggingface.co/Vchitect/Vchitect-XL-2B)
**:fire:The technical report is coming soon!**
## ๐ฅ Update and News
- [2024.09.14] ๐ฅ Inference code and [checkpoint](https://huggingface.co/Vchitect/Vchitect-XL-2B) are released.
## :astonished: Gallery
## Installation
### 1. Create a conda environment and install PyTorch
Note: You may want to adjust the CUDA version [according to your driver version](https://docs.nvidia.com/deploy/cuda-compatibility/#default-to-minor-version).
```bash
conda create -n VchitectXL -y
conda activate VchitectXL
conda install python=3.11 pytorch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 pytorch-cuda=12.1 -c pytorch -c nvidia -y
```
### 2. Install dependencies
```bash
pip install -r requirements.txt
```
## Inference
**First download the [checkpoint](https://huggingface.co/Vchitect/Vchitect-XL-2B).**
~~~bash
save_dir=$1
ckpt_path=$2
python inference.py --test_file assets/test.txt --save_dir "${save_dir}" --ckpt_path "${ckpt_path}"
~~~
In inference.py, arguments for inference:
- **num_inference_steps**: Denoising steps, default is 100
- **guidance_scale**: CFG scale to use, default is 7.5
- **width**: The width of the output video, default is 768
- **height**: The height of the output video, default is 432
- **frames**: The number of frames, default is 40
The results below were generated using the example prompt.
A snowy forest landscape with a dirt road running through it. The road is flanked by trees covered in snow, and the ground is also covered in snow. The sun is shining, creating a bright and serene atmosphere. The road appears to be empty, and there are no people or animals visible in the video.
The video opens with a breathtaking view of a starry sky and vibrant auroras. The camera pans to reveal a glowing black hole surrounded by swirling, luminescent gas and dust. Below, an enchanted forest of bioluminescent trees glows softly. The scene is a mesmerizing blend of cosmic wonder and magical landscape.
The base T2V model supports generating videos with resolutions up to 720x480 and 8fps. Then๏ผ[VEnhancer](https://github.com/Vchitect/VEnhancer) is used to upscale the resolution to 2K and interpolate the frame rate to 24fps.
## ๐ License
This code is licensed under Apache-2.0. The framework is fully open for academic research and also allows free commercial usage.
## Disclaimer
We disclaim responsibility for user-generated content. The model was not trained to realistically represent people or events, so using it to generate such content is beyond the model's capabilities. It is prohibited for pornographic, violent and bloody content generation, and to generate content that is demeaning or harmful to people or their environment, culture, religion, etc. Users are solely liable for their actions. The project contributors are not legally affiliated with, nor accountable for users' behaviors. Use the generative model responsibly, adhering to ethical and legal standards.
