Zeqiang Lai

I think the projective image of GAN inversion is pretty good, and the problem you face is the flaw in the DragGAN algorithm.

Well, I don't think this problem is specific for real image. What I mean is that the DragGAN algorithm could fail even if the image is synthetic by GAN without...

Wow, I haven't dive into the GAN inversion that original DragGAN paper uses before, but I think it would be a good idea to try more advanced inversion techniques.

Yes, you need GPU. It might be possible to run it with CPU, but it would be extremely slow and I didn't try it.

> I get this error aswell. I have an NVIDIA gpu. Stable diffusion runs fine on it on this install. `torch.cuda.is_available()` returns true > > i am using ubuntu You...

> @Zeqiang-Lai I currently do not have a Nvidia GPU but was thinking about buying one. Do you have any recommendations for GPUs that work very well with your DragGAN...

You could comment this line for it. https://github.com/Zeqiang-Lai/DragGAN/blob/24e27e4889a37388dc9bf998f79ac08d1802a8fc/gradio_app.py#L142

It should run without any special setup. Could you run the following snippet with python interpreter at your env and see if it print True ? ``` import torch print(torch.cuda.is_available())...

It might be, but I could not give a certain answer. Another option is to use our online colab demo where you could obtain a free GPU from google.

> online collab demo is throwing the same error. Did you select a GPU via Runtime/Change runtime type ?