InvokeAI/invokeai/backend/flux/modules/autoencoder.py at 6ae46d7c8b1f79764a33018173cd3efe55bf3e3a - InvokeAI - AtHeartEngineering

github/InvokeAI

mirror of https://github.com/invoke-ai/InvokeAI.git synced 2026-04-23 03:00:31 -04:00

Files

Ryan Dick a808ce81fd Replace swish() with torch.nn.functional.silu(h). They are functionally equivalent, but in my test VAE deconding was ~8% faster after the change.

2024-08-26 20:17:50 -04:00

10 KiB

Raw Blame History

View Raw