-
In your release model, the final loss is about 25 on training data, is that anything wrong? What the loss should be when the model converge normally？
-
Hi, thanks for the contribution!
Using stylegan2-ada, is it possible to generate consecutive frames of a video? (such as sequences in the KITTI/Cityscapes dataset)
I am not talking about style tra…
ffabi updated
3 years ago
-
RuntimeError: CUDA error: out of memory
My server is used by many people，this mistake has been repeated recently.
I try to change code to run in CPU machine ,but always failed.May you give me a ha…
-
Hey there,
first, thank you for your amazing work with this pytorch stylegan, i got it to work quite flawlessly.
I trained on a quite small custom dataset on the free gpu on google colab for severa…
-
In the end of the section _Image Generation Results_, some "Forthcoming papers" from google brain team are mentioned. Are they published yet? If yes, could you provide some links?
-
Hi! Thanks for sharing the great work!
I have some questions about FsFont.
Compare Ablation part and Experimental results, the model without any new module (the last row in Ablation studies table, …
-
-
Hello,
When using slow style, I get really nice results after 100-200 iterations but if I train a model with the same style image I never get results that look anything similar to slow style. Even af…
-
I have no error I imported all modules but the PhotoLab is not working. I see the app but there is no option to add image. Please help.
![image](https://user-images.githubusercontent.com/122890504/23…
-
Hi, I am new to StyleGAN. I want write a simple inference demo to generate a single image using a simple noise latent vector by random.
I am currently got this:
```python
"""
Generate …