open-mmlab/PIA
[CVPR 2024] PIA, your Personalized Image Animator. Animate your images by text prompt, combing with Dreambooth, achieving stunning videos. PIA,你的个性化图像动画生成器,利用文本提示将图像变为奇妙的动画
PythonApache-2.0
Issues
- 1
different outputs with inference.py example
#40 opened by zekicinar - 2
Why not train conv_in.bias?
#34 opened by ryancll - 4
About the weight and bias of Conv_in
#32 opened by Tianhao-Qi - 4
- 6
about statistics in 'prepare_mask_coef_by_score'
#42 opened by yuminnko - 5
Training Details
#19 opened by ryancll - 1
- 1
缺少模型下载地址
#39 opened by fallbernana123456 - 0
how to train?
#41 opened by yy-victory - 2
- 0
Add more sampling methods?
#38 opened by ArianaStar - 3
- 4
Can PIA checkpoint be used in A1111 webui?
#18 opened by xpeng - 2
Model for SDXL?
#10 opened by foureyednymph - 2
pia.ckpt gdown url miss?
#25 opened by sunyuhan19981208 - 1
- 1
xFormers can't load C++/CUDA extensions. xFormers was built for: PyTorch 2.1.2+cu121 with CUDA 1201 (you have 2.1.2+cpu)
#30 opened by guahunyo - 0
- 1
cannot download pia.ckpt file vid gdown
#27 opened by feiyangsuo - 4
Please create demo colab
#4 opened by G-force78 - 2
demo give error
#12 opened by loboere - 1
The generated face easily collapses.
#24 opened by sunyuhan19981208 - 0
Training code release
#23 opened by Tianhao-Qi - 1
is this similar to LivePhoto?
#22 opened by Dibbidy - 0
AMD gpu support?
#20 opened by micbusin - 0
Training code release?
#14 opened by JoshonSmith - 1
Training code release?
#16 opened by mayuelala - 0
Training code 😊
#17 opened by mayuelala - 0
training code
#15 opened by mayuelala - 2
- 0
Training code availability
#8 opened by kowalgregy - 1
- 2
A way to create loop
#2 opened by C00reNUT