johannakarras/DreamPose
Official implementation of "DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion"
PythonMIT
Issues
- 1
- 0
densepose?
#74 opened by xingmurong - 3
Demo run issue
#41 opened by RunqiWang77 - 0
To calculate FID and FID-VID scores
#73 opened by likith1908 - 0
- 0
- 4
- 0
configuring the environment
#69 opened by gitPZH - 2
- 2
Output verification
#46 opened by jmahajan117 - 1
Logging_dir
#68 opened by Nwosu-Ihueze - 5
how should i kill this error?
#54 opened by zzk88862 - 8
dict key error in demo
#49 opened by DmitriyPin - 3
Colab problem: The expanded size of the tensor (10) must match the existing size (11) at a non-singleton dimension 1.
#65 opened by steinhaug - 4
RuntimeError Tensor size mismatch after following the instructions mentioned on this repo README
#60 opened by sajidahmed12 - 0
OSError: Unable to load weights from pytorch checkpoint file. If you tried to load a PyTorch model from a TF 2.0 checkpoint, please set from_tf=True.
#67 opened by caojiehui - 0
- 0
Unseen image
#63 opened by eastchun - 0
which DreamPoseDataset used in train.py?
#64 opened by pikeyang - 1
- 0
Errors with adapter
#62 opened by 351246241 - 4
CUDA out of memory
#42 opened by abdelrahmanabdelghany - 1
Hand + Face of Human Pose
#52 opened by p0mad - 0
Imagen Video or Stable Diffusion?
#58 opened by forever208 - 1
- 0
Training Time
#56 opened by CacacaLalala - 0
How to perform distributed training.
#55 opened by jiazheng-xing - 1
Wrong demo output
#38 opened by laiyingxin2 - 1
Training Script Issue
#53 opened by jmahajan117 - 0
Eval Script?
#51 opened by jmahajan117 - 3
- 1
out of memory
#50 opened by chenbolin-master - 2
error in demo
#48 opened by DmitriyPin - 3
GPU OOM when multi-gpu training
#40 opened by flamehaze1115 - 7
finetuning-unet causes error
#45 opened by jmahajan117 - 1
Fine-tuned on multiple input images
#36 opened by rohitpaul23 - 3
unet.conv_in.weight[:, 3:] = torch.zeros(unet.conv_in.weight[:, 3:].shape) I assume 3 should be 4
#37 opened by zhangtao22 - 4
The implementation of 5 consecutive poses
#31 opened by Wangt-CN - 0
The input size of the model
#39 opened by linziqu - 2
difference in training script and paper
#34 opened by adwardlee - 1
- 10
Issues with Fine-tuning
#25 opened by ilovecv - 2
How did you train model specifically? And when fine-tuning on both UNet and VAE, did you also just use the single frame_50.png image to finetune?
#32 opened by zhangtao22 - 0
do you use densepose's original pickle.dump(context["results"], hFile) to save pkl?If I use this, I can't open it with your densepose.py.It said invalid
#30 opened by zhangtao22 - 1
Demo run issue
#27 opened by YuanZi1501040205 - 1
where is this Deep_Fashion_Dataset/img_highres and what does ../UBC_Fashion_Dataset/train-frames/*/*png' refer to?
#29 opened by zhangtao22 - 0
solved
#28 opened by zhangtao22 - 4
fine-tuning is quite GPU memory consuming
#26 opened by weizmann - 4
image resize error when fine-tuning UNet
#23 opened by weizmann - 2
No datasets modules
#24 opened by david-svitov