How to fine tune stable diffusion: how we made the text-to-pokemon model at Lambda
Stable Diffusion is great at many things, but not great at everything, and getting results in a particular style or appearance often involves a lot of work ...
Recent
Keeping an eye on your GPUs - GPU monitoring tools compared
So you’ve just bought yourself some nice shiny GPUs for your next awesome deep learning project and you’ve got them busily working away for you. You can hear ...
StyleGAN 3
Key points StyleGAN3 generates state of the art results for un-aligned datasets and looks much more natural in motion Use of fourier features, filtering, 1x1 ...
To top