Fix [occasionally] missing text encoder attn modules

Should fix kohya-ss#1952
I added alternative name for CLIPAttention.
I have no idea why this name changed.
Now it should accept both names.

Author: Ivan Chikish

networks/dylora.py

@@ -268,7 +268,7 @@ def create_network_from_weights(multiplier, file, vae, text_encoder, unet, weigh
 class DyLoRANetwork(torch.nn.Module):
     UNET_TARGET_REPLACE_MODULE = ["Transformer2DModel"]
     UNET_TARGET_REPLACE_MODULE_CONV2D_3X3 = ["ResnetBlock2D", "Downsample2D", "Upsample2D"]
-    TEXT_ENCODER_TARGET_REPLACE_MODULE = ["CLIPAttention", "CLIPMLP"]
+    TEXT_ENCODER_TARGET_REPLACE_MODULE = ["CLIPAttention", "CLIPSdpaAttention", "CLIPMLP"]
     LORA_PREFIX_UNET = "lora_unet"
     LORA_PREFIX_TEXT_ENCODER = "lora_te"
 

networks/lora.py

@@ -866,7 +866,7 @@ class LoRANetwork(torch.nn.Module):
 
     UNET_TARGET_REPLACE_MODULE = ["Transformer2DModel"]
     UNET_TARGET_REPLACE_MODULE_CONV2D_3X3 = ["ResnetBlock2D", "Downsample2D", "Upsample2D"]
-    TEXT_ENCODER_TARGET_REPLACE_MODULE = ["CLIPAttention", "CLIPMLP"]
+    TEXT_ENCODER_TARGET_REPLACE_MODULE = ["CLIPAttention", "CLIPSdpaAttention", "CLIPMLP"]
     LORA_PREFIX_UNET = "lora_unet"
     LORA_PREFIX_TEXT_ENCODER = "lora_te"
 

networks/lora_diffusers.py

@@ -278,7 +278,7 @@ def merge_lora_weights(pipe, weights_sd: Dict, multiplier: float = 1.0):
 class LoRANetwork(torch.nn.Module):
     UNET_TARGET_REPLACE_MODULE = ["Transformer2DModel"]
     UNET_TARGET_REPLACE_MODULE_CONV2D_3X3 = ["ResnetBlock2D", "Downsample2D", "Upsample2D"]
-    TEXT_ENCODER_TARGET_REPLACE_MODULE = ["CLIPAttention", "CLIPMLP"]
+    TEXT_ENCODER_TARGET_REPLACE_MODULE = ["CLIPAttention", "CLIPSdpaAttention", "CLIPMLP"]
     LORA_PREFIX_UNET = "lora_unet"
     LORA_PREFIX_TEXT_ENCODER = "lora_te"
 

networks/lora_fa.py

@@ -755,7 +755,7 @@ class LoRANetwork(torch.nn.Module):
 
     UNET_TARGET_REPLACE_MODULE = ["Transformer2DModel"]
     UNET_TARGET_REPLACE_MODULE_CONV2D_3X3 = ["ResnetBlock2D", "Downsample2D", "Upsample2D"]
-    TEXT_ENCODER_TARGET_REPLACE_MODULE = ["CLIPAttention", "CLIPMLP"]
+    TEXT_ENCODER_TARGET_REPLACE_MODULE = ["CLIPAttention", "CLIPSdpaAttention", "CLIPMLP"]
     LORA_PREFIX_UNET = "lora_unet"
     LORA_PREFIX_TEXT_ENCODER = "lora_te"