Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://yingqinghe.github.io/LVDM/

LVDM: Latent Video Diffusion Models for High-Fidelity Long Video Generation
https://yingqinghe.github.io/LVDM/

Last synced: about 1 month ago
JSON representation

LVDM: Latent Video Diffusion Models for High-Fidelity Long Video Generation

Awesome Lists containing this project

README 

        





 LVDM: Latent Video Diffusion Models for High-Fidelity Long Video Generation  
 



        





    Yingqing He 1  

    Tianyu Yang 2 

    Yong Zhang 2 

    Ying Shan 2 

    Qifeng Chen 1  








    1 The Hong Kong University of Science and Technology   2 Tencent AI Lab  










TL;DR: An efficient video diffusion model that can:  

1️⃣ conditionally generate videos based on input text;  

2️⃣ unconditionally generate videos with thousands of frames.










## 🍻 Results

### ☝️ Text-to-Video Generation



  

  "A corgi is swimming fastly"

  "astronaut riding a horse"

  "A glass bead falling into water with a huge splash. Sunset in the background"

  "A beautiful sunrise on mars. High definition, timelapse, dramaticcolors."

  "A bear dancing and jumping to upbeat music, moving his whole body."

  "An iron man surfing in the sea. cartoon style"

  

  

  

  

  

  

  



### ✌️ Unconditional Long Video Generation (40 seconds)



  

  

  

  

  

  

  



## ⏳ TODO

- [x] Release pretrained text-to-video generation models and inference code

- [x] Release unconditional video generation models

- [x] Release training code

- [ ] Update training and sampling for long video generation





---

## ⚙️ Setup



### Install Environment via Anaconda

```bash

conda create -n lvdm python=3.8.5

conda activate lvdm

pip install -r requirements.txt

```

### Pretrained Models and Used Datasets



Download via linux commands:

```

mkdir -p models/ae

mkdir -p models/lvdm_short

mkdir -p models/t2v



# sky timelapse

wget -O models/ae/ae_sky.ckpt https://huggingface.co/Yingqing/LVDM/resolve/main/ae/ae_sky.ckpt

wget -O models/lvdm_short/short_sky.ckpt https://huggingface.co/Yingqing/LVDM/resolve/main/lvdm_short/short_sky.ckpt  



# taichi

wget -O models/ae/ae_taichi.ckpt https://huggingface.co/Yingqing/LVDM/resolve/main/ae/ae_taichi.ckpt

wget -O models/lvdm_short/short_taichi.ckpt https://huggingface.co/Yingqing/LVDM/resolve/main/lvdm_short/short_taichi.ckpt



# text2video

wget -O models/t2v/model.ckpt https://huggingface.co/Yingqing/LVDM/resolve/main/lvdm_short/t2v.ckpt

```



Download manually:

- Sky Timelapse: [VideoAE](https://huggingface.co/Yingqing/LVDM/blob/main/ae/ae_sky.ckpt), [LVDM_short](https://huggingface.co/Yingqing/LVDM/blob/main/lvdm_short/short_sky.ckpt), [LVDM_pred](TBD), [LVDM_interp](TBD), [dataset](https://github.com/weixiong-ur/mdgan)

- Taichi: [VideoAE](https://huggingface.co/Yingqing/LVDM/blob/main/ae/ae_taichi.ckpt), [LVDM_short](https://huggingface.co/Yingqing/LVDM/blob/main/lvdm_short/short_taichi.ckpt), [dataset](https://github.com/AliaksandrSiarohin/first-order-model/blob/master/data/taichi-loading/README.md)

- Text2Video: [model](https://huggingface.co/Yingqing/LVDM/blob/main/lvdm_short/t2v.ckpt)



---

## 💫 Inference 

### Sample Short Videos 

- unconditional generation



```

bash shellscripts/sample_lvdm_short.sh

```

- text to video generation

```

bash shellscripts/sample_lvdm_text2video.sh

```



### Sample Long Videos 

```

bash shellscripts/sample_lvdm_long.sh

```



---

## 💫 Training



### Train video autoencoder

```

bash shellscripts/train_lvdm_videoae.sh 

```

- remember to set `PROJ_ROOT`, `EXPNAME`, `DATADIR`, and `CONFIG`.



### Train unconditional lvdm for short video generation

```

bash shellscripts/train_lvdm_short.sh

```

- remember to set `PROJ_ROOT`, `EXPNAME`, `DATADIR`, `AEPATH` and `CONFIG`.



### Train unconditional lvdm for long video generation

```

# TBD

```



---

## 💫 Evaluation

```

bash shellscripts/eval_lvdm_short.sh

```

- remember to set `DATACONFIG`, `FAKEPATH`, `REALPATH`, and `RESDIR`.

---



## 📃 Abstract

AI-generated content has attracted lots of attention recently, but photo-realistic video synthesis is still challenging. Although many attempts using GANs and autoregressive models have been made in this area, the visual quality and length of generated videos are far from satisfactory. Diffusion models have shown remarkable results recently but require significant computational resources. To address this, we introduce lightweight video diffusion models by leveraging a low-dimensional 3D latent space, significantly outperforming previous pixel-space video diffusion models under a limited computational budget. In addition, we propose hierarchical diffusion in the latent space such that longer videos with more than one thousand frames can be produced. To further overcome the performance degradation issue for long video generation, we propose conditional latent perturbation and unconditional guidance that effectively mitigate the accumulated errors during the extension of video length. Extensive experiments on small domain datasets of different categories suggest that our framework generates more realistic and longer videos than previous strong baselines. We additionally provide an extension to large-scale text-to-video generation to demonstrate the superiority of our work. Our code and models will be made publicly available.





## 🔮 Pipeline





    




---

## 😉 Citation



```

@article{he2022lvdm,

      title={Latent Video Diffusion Models for High-Fidelity Long Video Generation}, 

      author={Yingqing He and Tianyu Yang and Yong Zhang and Ying Shan and Qifeng Chen},

      year={2022},

      eprint={2211.13221},

      archivePrefix={arXiv},

      primaryClass={cs.CV}

}

```



## 🤗 Acknowledgements

We built our code partially based on [latent diffusion models](https://github.com/CompVis/latent-diffusion) and [TATS](https://github.com/SongweiGe/TATS). Thanks the authors for sharing their awesome codebases! We aslo adopt Xintao Wang's [Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN) for upscaling our text-to-video generation results. Thanks for their wonderful work!