PIA：Personalized Image Animator

PIA: Your Personalized Image Animator via Plug-and-Play Modules in Text-to-Image Models

Yiming Zhang†, Zhening Xing†, Yanhong Zeng, Youqing Fang, Kai Chen*

(*Corresponding Author, †Equal Contribution)

You may also want to try other project from our team:

PIA is a personalized image animation method which can generate videos with high motion controllability and strong text and image alignment.

What's New

[2024/01/03] Add Replicate Demo & API!

[2024/01/03] Add third-party Colab!

[2023/12/28] PIA can animate a 1024x1024 image with just 16GB of GPU memory with scaled_dot_product_attention!

[2023/12/25] HuggingFace demo is available now! 🤗 Hub

[2023/12/22] Release the model and demo of PIA. Try it to make your personalized movie!

• Online Demo on OpenXLab
• Checkpoint on Google Drive or

Setup

Prepare Environment

Use the following command to install Pytorch==2.0.0 and other dependencies:

conda env create -f environment-pt2.yaml
conda activate pia

If you want to use lower version of Pytorch (e.g. 1.13.1), you can use the following command:

conda env create -f environment.yaml
conda activate pia

We strongly recommand you to use Pytorch==2.0.0 which supports scaled_dot_product_attention for memory-efficient image animation.

Download checkpoints

git lfs install
git clone https://huggingface.co/runwayml/stable-diffusion-v1-5 models/StableDiffusion/

bash download_bashscripts/1-RealisticVision.sh
bash download_bashscripts/2-RcnzCartoon.sh
bash download_bashscripts/3-MajicMix.sh

bash download_bashscripts/0-PIA.sh

You can also download pia.ckpt through link on Google Drive or HuggingFace.

Put checkpoints as follows:

└── models
    ├── DreamBooth_LoRA
    │   ├── ...
    ├── PIA
    │   ├── pia.ckpt
    └── StableDiffusion
        ├── vae
        ├── unet
        └── ...

Usage

Image Animation

Image to Video result can be obtained by:

python inference.py --config=example/config/lighthouse.yaml
python inference.py --config=example/config/harry.yaml
python inference.py --config=example/config/majic_girl.yaml

Run the command above, you will get:

Input Image	lightning, lighthouse	sun rising, lighthouse	fireworks, lighthouse
Input Image	1boy smiling	1boy playing the magic fire	1boy is waving hands
Input Image	1girl is smiling	1girl is crying	1girl, snowing

Motion Magnitude

You can control the motion magnitude through the parameter magnitude:

python inference.py --config=example/config/xxx.yaml --magnitude=0 # Small Motion
python inference.py --config=example/config/xxx.yaml --magnitude=1 # Moderate Motion
python inference.py --config=example/config/xxx.yaml --magnitude=2 # Large Motion

Examples:

python inference.py --config=example/config/labrador.yaml
python inference.py --config=example/config/bear.yaml
python inference.py --config=example/config/genshin.yaml

Input Image & Prompt	Small Motion	Moderate Motion	Large Motion
a golden labrador is running
1bear is walking, ...
cherry blossom, ...

Style Transfer

To achieve style transfer, you can run the command(Please don't forget set the base model in xxx.yaml):

Examples:

python inference.py --config example/config/concert.yaml --style_transfer
python inference.py --config example/config/ania.yaml --style_transfer

Input Image & Base Model	1man is smiling	1man is crying	1man is singing
Realistic Vision
RCNZ Cartoon 3d
	1girl smiling	1girl open mouth	1girl is crying, pout
RCNZ Cartoon 3d

Loop Video

You can generate loop by using the parameter --loop

python inference.py --config=example/config/xxx.yaml --loop

Examples:

python inference.py --config=example/config/lighthouse.yaml --loop
python inference.py --config=example/config/labrador.yaml --loop

Input Image	lightning, lighthouse	sun rising, lighthouse	fireworks, lighthouse
Input Image	labrador jumping	labrador walking	labrador running

AnimateBench

We have open-sourced AnimateBench on HuggingFace which includes images, prompts and configs to evaluate PIA and other image animation methods.

Contact Us

Yiming Zhang: [email protected]

Zhening Xing: [email protected]

Yanhong Zeng: [email protected]

Acknowledgements

The code is built upon AnimateDiff, Tune-a-Video and PySceneDetect