If you find this repository helpful, please consider giving us a star⭐!
This repository contains an simple and unofficial implementation of Animate Anyone. This project is built upon magic-animate and AnimateDiff.
The first training phase basic test passed, currently in training and testing the second phase.
Training may be slow due to GPU shortage.😢
It only takes a few days to release the weights.😄
Special thanks to Zhenzhi Wang for assistance with code development and training. The current version of the face also has some artifacts. Also, this is a model trained on a UBC dataset rather than a large-scale dataset.
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!
In the current version, we recommend training on 8 or 16 A100,H100 (80G) at 512 or 768 resolution. Low resolution (256,384) does not give good results!!!(VAE is very poor at reconstruction at low resolution.)
- Release Training Code.
- Release Inference Code.
- Release Unofficial Pre-trained Weights. (Note:Train on public datasets instead of large-scale private datasets, just for academic research.🤗)
- Release Gradio Demo.
bash fast_env.sh
python3 -m demo.gradio_animate
If you only have a GPU with 24 GB of VRAM, I recommend inference at resolution 512 and below.
torchrun --nnodes=8 --nproc_per_node=8 train.py --config configs/training/train_stage_1.yaml
torchrun --nnodes=8 --nproc_per_node=8 train.py --config configs/training/train_stage_2.yaml
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.
My response may be slow, please don't ask me nonsense questions.