pidginred

@AliaksandrSiarohin `sigma=1.5` does not work for 1024x1024 source images (with scale factor of 0.0625). I get the following error: ``` File "C:\Users\admin\git\first-order-model\modules\util.py", line 180, in forward out = torch.cat([out, skip],...

@AliaksandrSiarohin Certainly! Here are the changes I made (for 1024x1024 / 0.0625) & the full error stack: ## Diffs ```diff diff --git a/config/vox-256.yaml b/config/vox-256.yaml index abfe9a2..10fce42 100644 --- a/config/vox-256.yaml +++...

@eps696 What was your scale factor for 1024x1024? And did you get a proper output?

@eps696 Confirmed that worked. However, I lost almost complete eye & mouth tracking (compared to 256x256), and it results in lots of weird artifacts and very poor quality output. Are...