mirror of
https://github.com/kohya-ss/sd-scripts.git
synced 2026-04-09 06:45:09 +00:00
Merge branch 'dev' into sd3
This commit is contained in:
@@ -752,6 +752,8 @@ Not available yet.
|
|||||||
[__Change History__](#change-history) is moved to the bottom of the page.
|
[__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。
|
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)
|
[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.
|
The development version is in the `dev` branch. Please check the dev branch for the latest changes.
|
||||||
@@ -895,6 +897,11 @@ The majority of scripts is licensed under ASL 2.0 (including codes from Diffuser
|
|||||||
|
|
||||||
## Change History
|
## 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
|
### Jan 17, 2025 / 2025-01-17 Version 0.9.0
|
||||||
|
|
||||||
- __important__ The dependent libraries are updated. Please see [Upgrade](#upgrade) and update the libraries.
|
- __important__ The dependent libraries are updated. Please see [Upgrade](#upgrade) and update the libraries.
|
||||||
|
|||||||
@@ -268,7 +268,7 @@ def create_network_from_weights(multiplier, file, vae, text_encoder, unet, weigh
|
|||||||
class DyLoRANetwork(torch.nn.Module):
|
class DyLoRANetwork(torch.nn.Module):
|
||||||
UNET_TARGET_REPLACE_MODULE = ["Transformer2DModel"]
|
UNET_TARGET_REPLACE_MODULE = ["Transformer2DModel"]
|
||||||
UNET_TARGET_REPLACE_MODULE_CONV2D_3X3 = ["ResnetBlock2D", "Downsample2D", "Upsample2D"]
|
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_UNET = "lora_unet"
|
||||||
LORA_PREFIX_TEXT_ENCODER = "lora_te"
|
LORA_PREFIX_TEXT_ENCODER = "lora_te"
|
||||||
|
|
||||||
|
|||||||
@@ -866,7 +866,7 @@ class LoRANetwork(torch.nn.Module):
|
|||||||
|
|
||||||
UNET_TARGET_REPLACE_MODULE = ["Transformer2DModel"]
|
UNET_TARGET_REPLACE_MODULE = ["Transformer2DModel"]
|
||||||
UNET_TARGET_REPLACE_MODULE_CONV2D_3X3 = ["ResnetBlock2D", "Downsample2D", "Upsample2D"]
|
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_UNET = "lora_unet"
|
||||||
LORA_PREFIX_TEXT_ENCODER = "lora_te"
|
LORA_PREFIX_TEXT_ENCODER = "lora_te"
|
||||||
|
|
||||||
|
|||||||
@@ -278,7 +278,7 @@ def merge_lora_weights(pipe, weights_sd: Dict, multiplier: float = 1.0):
|
|||||||
class LoRANetwork(torch.nn.Module):
|
class LoRANetwork(torch.nn.Module):
|
||||||
UNET_TARGET_REPLACE_MODULE = ["Transformer2DModel"]
|
UNET_TARGET_REPLACE_MODULE = ["Transformer2DModel"]
|
||||||
UNET_TARGET_REPLACE_MODULE_CONV2D_3X3 = ["ResnetBlock2D", "Downsample2D", "Upsample2D"]
|
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_UNET = "lora_unet"
|
||||||
LORA_PREFIX_TEXT_ENCODER = "lora_te"
|
LORA_PREFIX_TEXT_ENCODER = "lora_te"
|
||||||
|
|
||||||
|
|||||||
@@ -755,7 +755,7 @@ class LoRANetwork(torch.nn.Module):
|
|||||||
|
|
||||||
UNET_TARGET_REPLACE_MODULE = ["Transformer2DModel"]
|
UNET_TARGET_REPLACE_MODULE = ["Transformer2DModel"]
|
||||||
UNET_TARGET_REPLACE_MODULE_CONV2D_3X3 = ["ResnetBlock2D", "Downsample2D", "Upsample2D"]
|
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_UNET = "lora_unet"
|
||||||
LORA_PREFIX_TEXT_ENCODER = "lora_te"
|
LORA_PREFIX_TEXT_ENCODER = "lora_te"
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user