InvokeAI/invokeai/backend/flux/modules
2024-08-26 20:17:50 -04:00
..
autoencoder.py 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
conditioner.py Attribute black-forest-labs/flux for much of the flux code 2024-08-26 20:17:50 -04:00
layers.py Attribute black-forest-labs/flux for much of the flux code 2024-08-26 20:17:50 -04:00