johannakarras / DreamPose

Official implementation of "DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion"

johannakarras/DreamPose Issues

which DreamPoseDataset used in train.py?
Updated 5 months ago
how to download the specific revision of Stable Diffusion weights?
Updated 5 months ago1
should utils/densepose.py change its file name?
Updated 5 months ago1
dict key error in demo
Updated 5 months ago7
Unseen image
Updated 5 months ago
RuntimeError Tensor size mismatch after following the instructions mentioned on this repo README
Updated 6 months ago2
Errors with adapter
Updated 6 months ago
CUDA out of memory
Updated 7 months ago4
how should i kill this error?
Updated 7 months ago4
Hand + Face of Human Pose
Updated 7 months ago1
Imagen Video or Stable Diffusion?
Updated 8 months ago
A very-related fancy project/repo, just wanna to share
Updated 8 months ago1
Training Time
Updated 9 months ago
How to perform distributed training.
Updated 9 months ago
Demo run issue
Updated 9 months ago2
Wrong demo output
Updated 10 months ago1
Training Script Issue
Closed 10 months ago1
Eval Script?
Updated 10 months ago
CUDA out of memory error while Fine-Tuning the DreamPose
Closed 10 months ago3
out of memory
Updated 10 months ago1
error in demo
Closed 10 months ago2
GPU OOM when multi-gpu training
Closed a year ago3
Output verification
Updated 10 months ago
finetuning-unet causes error
Closed 10 months ago7
Fine-tuned on multiple input images
Updated a year ago1
I trained on UBC Fashion Dataset，but the outcome is pretty bad.
Updated a year ago2
unet.conv_in.weight[:, 3:] = torch.zeros(unet.conv_in.weight[:, 3:].shape) I assume 3 should be 4
Closed a year ago3
The implementation of 5 consecutive poses
Closed a year ago4
The input size of the model
Updated a year ago
difference in training script and paper
Closed a year ago2
done
Closed a year ago1
Issues with Fine-tuning
Closed a year ago10
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?
Updated a year ago2
hair style is flickering
Closed a year ago2
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
Closed a year ago
Demo run issue
Closed a year ago1
where is this Deep_Fashion_Dataset/img_highres and what does ../UBC_Fashion_Dataset/train-frames/*/*png' refer to?
Closed a year ago1
solved
Closed a year ago
fine-tuning is quite GPU memory consuming
Closed a year ago4
image resize error when fine-tuning UNet
Closed a year ago4
Environment issue: cannot import name 'BasicTransformerBlock' from 'diffusers.models'
Closed a year ago2
files and classes missing error.
Closed a year ago3
No datasets modules
Closed a year ago2
How to generate densepose.npy file? which densepose model can i use?
Closed a year ago5
help: fine-tuning issue
Closed a year ago1
fixed
Closed a year ago
fixed
Closed a year ago
The implementation of adapter
Closed a year ago1
Finetune the VAE decoder
Closed a year ago1
what env is used?
Closed a year ago2