ray0809

the input_size and out_size of big-lama

4

Hi, Firstly, Thank you for making such a great project open source. I found the out_size in released big-lama config.yaml is 256, was the big-lama model trained with images' size...

Hi Yanhong, I found the configs of different dataset(such as lr, optimizer params, niters and so on) are all the same, is it the right params when you are traning...

Hi, Firstly, Thanks for your sharing the code. When I read your code, I found the last layer in generator is nn.Tanh, but the inputs of images with range [0,...

[BUG]: fine-tune with stable diffusion

3

### 🐛 Describe the bug when I running the training example with cifar10, It broken with an error `RuntimeError: Expected is_sm80 to be true, but got false.` As mentioned from...