/AnimateAnyone-unofficial

Unofficial Implementation of Animate Anyone

Primary LanguagePython

Unofficial Implementation of Animate Anyone

Overview

This repository contains an simple and unofficial implementation of Animate Anyone. This project is built upon magic-animate and AnimateDiff.

News 🤗🤗🤗

The first training phase basic test passed, currently in training and testing the second phase.

Training may be slow due to GPU shortage.😢

Note !!!

This project is under continuous development in part-time, there may be bugs in the code, welcome to correct them, I will optimize the code after the pre-trained model is released!

Requirements

Same as magic-animate.

ToDo

  • Release Training Code.
  • DeepSpeed + Accelerator Training
  • Release Inference Code and unofficial pre-trained weights.

Training

First Stage

torchrun --nnodes=1 --nproc_per_node=1 train.py --config configs/training/train_stage_1.yaml

Second Stage

torchrun --nnodes=1 --nproc_per_node=1 train.py --config configs/training/train_stage_2.yaml

Inference

First Stage

python3 -m pipelines.animation_stage_1 --config configs/prompts/animation_stage_1.yaml

Second Stage

Acknowledgements

Special thanks to the original authors of the Animate Anyone project and the contributors to the magic-animate and AnimateDiff repository for their open research and foundational work that inspired this unofficial implementation.

Email

guoqin@stu.pku.edu.cn