Merge branch 'main' into dev

Author: kohya-ss

README.md

@@ -3,6 +3,8 @@ This repository contains training, generation and utility scripts for Stable Dif
 [__Change History__](#change-history) is moved to the bottom of the page. 
 更新履歴は[ページ末尾](#change-history)に移しました。
 
+Latest update: 2025-03-21 (Version 0.9.1)
+
 [日本語版READMEはこちら](./README-ja.md)
 
 The development version is in the `dev` branch. Please check the dev branch for the latest changes.
@@ -146,6 +148,11 @@ The majority of scripts is licensed under ASL 2.0 (including codes from Diffuser
 
 ## Change History
 
+### Mar 21, 2025 /  2025-03-21 Version 0.9.1
+
+- Fixed a bug where some of LoRA modules for CLIP Text Encoder were not trained. Thank you Nekotekina for PR [#1964](https://github.com/kohya-ss/sd-scripts/pull/1964)
+  - The LoRA modules for CLIP Text Encoder are now 264 modules, which is the same as before. Only 88 modules were trained in the previous version. 
+
 ### Jan 17, 2025 /  2025-01-17 Version 0.9.0
 
 - __important__ The dependent libraries are updated. Please see [Upgrade](#upgrade) and update the libraries.

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"