Ryan Dick bcd29c5d74 Remove all cases where we check the 'model.device'. This is no longer trustworthy now that partial loading is permitted.

2025-01-07 00:31:00 +00:00

..

autoencoder.py

Add FLUX VAE support to ImageToLatentsInvocation.

2024-09-02 09:38:17 -04:00

conditioner.py

Remove all cases where we check the 'model.device'. This is no longer trustworthy now that partial loading is permitted.

2025-01-07 00:31:00 +00:00

layers.py

Replace custom RMSNorm implementation with torch.nn.functional.rms_norm(...) for improved speed.

2024-11-29 12:32:50 -05:00