Vlogger

This repository is the official implementation of Vlogger:

Demo generated by our Vlogger: Teddy Travel

Setup

Prepare Environment

conda create -n vlogger python==3.10.11
conda activate vlogger
pip install -r requirements.txt

Download our model and T2I base model

Our model is based on Stable diffusion v1.4, you may download Stable Diffusion v1-4 and OpenCLIP-ViT-H-14 to the director of pretrained . Download our model(ShowMaker) checkpoint (from google drive or hugging face) and save to the directory of pretrained

Now under ./pretrained, you should be able to see the following:

├── pretrained
│   ├── ShowMaker.pt
│   ├── stable-diffusion-v1-4
│   ├── OpenCLIP-ViT-H-14
│   │   ├── ...
└── └── ├── ...
        ├── ...

Usage

Inference for (T+I)2V

Run the following command to get the (T+I)2V results:

python sample_scripts/with_mask_sample.py

The generated video will be saved in results/mask_no_ref.

Inference for (T+I+ref)2V

Run the following command to get the (T+I+ref)2V results:

python sample_scripts/with_mask_ref_sample.py

The generated video will be saved in results/mask_ref.

Inference for LLM planning and make reference image

Run the following command to get script, actors and protagonist:

python sample_scripts/vlog_write_script.py

The generated scripts will be saved in results/vlog/$your_story_dir/script.

The generated reference images will be saved in results/vlog/$your_story_dir/img.

!!!important: Enter your openai key in the 7th line of the file vlogger/planning_utils/gpt4_utils.py

Inference for vlog generation

Run the following command to get the vlog:

python sample_scripts/vlog_read_script_sample.py

The generated scripts will be saved in results/vlog/$your_story_dir/video.

More Details

You may modify configs/with_mask_sample.yaml to change the (T+I)2V conditions.

You may modify configs/with_mask_ref_sample.yaml to change the (T+I+ref)2V conditions. For example:

ckpt is used to specify a model checkpoint.

text_prompt is used to describe the content of the video.

input_path is used to specify the path to the image.

ref_path is used to specify the path to the reference image.

save_path is used to specify the path to the generated video.

Results

(T+Ref)2V Results

Reference Image	Output Video
Scene Reference	Fireworks explode over the pyramids.
Scene Reference	The Great Wall burning with raging fire.
Object Reference	A cat is running on the beach.

(T+I)2V Results

Input Image	Output Video
	Underwater environment cosmetic bottles.
	A big drop of water falls on a rose petal.
	A fish swims past an oriental woman.
	Cinematic photograph. View of piloting aaero.
	Planet hits earth.

T2V Results

Output Video
A deer looks at the sunset behind him.	A duck is teaching math to another duck.
Bezos explores tropical rainforest.	Light blue water lapping on the beach.

BibTeX

@article{zhuang2024vlogger,
title={Vlogger: Make Your Dream A Vlog},
author={Zhuang, Shaobin and Li, Kunchang and Chen, Xinyuan and Wang, Yaohui and Liu, Ziwei and Qiao, Yu and Wang, Yali},
journal={arXiv preprint arXiv:2401.09414},
year={2024}
}

@article{chen2023seine,
title={SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction},
author={Chen, Xinyuan and Wang, Yaohui and Zhang, Lingjun and Zhuang, Shaobin and Ma, Xin and Yu, Jiashuo and Wang, Yali and Lin, Dahua and Qiao, Yu and Liu, Ziwei},
journal={arXiv preprint arXiv:2310.20700},
year={2023}
}

@article{wang2023lavie,
  title={LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models},
  author={Wang, Yaohui and Chen, Xinyuan and Ma, Xin and Zhou, Shangchen and Huang, Ziqi and Wang, Yi and Yang, Ceyuan and He, Yinan and Yu, Jiashuo and Yang, Peiqing and others},
  journal={arXiv preprint arXiv:2309.15103},
  year={2023}
}

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.

Contact Us

Shaobin Zhuang: zhuangshaobin@pjlab.org.cn

Kunchang Li: likunchang@pjlab.org.cn

Xinyuan Chen: chenxinyuan@pjlab.org.cn

Yaohui Wang: wangyaohui@pjlab.org.cn

Acknowledgements

The code is built upon SEINE, LaVie, diffusers and Stable Diffusion, we thank all the contributors for open-sourcing.

License

The code is licensed under Apache-2.0, model weights are fully open for academic research and also allow free commercial usage. To apply for a commercial license, please contact zhuangshaobin@pjlab.org.cn.