-
Hello!
I tried to generate the interpolation video with the pre-trained CelebA-HQ network and found that the reference.jpg that is saved before the video generation step does not feature style-mix…
-
Namespace(batch_size=8, beta1=0.0, beta2=0.99, checkpoint_dir='expr/checkpoints/celeba_hq', ds_iter=100000, eval_dir='expr/eval', eval_every=50000, f_lr=1e-06, hidden_dim=512, img_size=256, inp_dir='a…
-
AssertionError: ./HFGI3D-main/test_celeba_img_dataset is not a valid directory
Could you provide the datasets or the link?
{
# Face Datasets (In the paper: FFHQ - train, CelebAHQ - test)
'ff…
-
It seems that when merging CelebA-Mask-HQ masks the order of masks matters. In particular one should first render "skin" and only then "ear".
Compare:
https://github.com/taki0112/SPADE-Tensorflow…
-
Mentioned in the paper, the quantitative evaluation blind method is CelebA-HQ dataset, I wonder if the images used in experiment is all images of CelebA-HQ, which is totoally 30K images?
-
Hello, can you upload the Data used to train and models in GitHub?
-
The above exception was raised in running download_celebA_HQ.py
Command:
python download_celebA_HQ.py ./img_align_celeba
Output log:
Deal with file: deltas00000.zip
[*] ./img_align_celeba…
JL321 updated
4 years ago
-
Prepare Diffusion Models
For CelebA-HQ identity and gender datasets, we use the diffusion model weights pretrained on CelebA-HQ from [DiffusionCLIP](https://github.com/gwang-kim/DiffusionCLIP): [IR-S…
-
Hello,
Thanks for the great work! However I'm facing some errors when generating the images dataset. One of them is when I executed the command `python2 h5tool.py create_celeba_hq file_name_to_save /…
-
## Describe the bug
Loading huggan/CelebA-HQ throws pyarrow.lib.ArrowInvalid
## Steps to reproduce the bug
```python
from datasets import load_dataset
dataset = load_dataset('huggan/CelebA-HQ')…