Merge branch 'dev' into deep-speed

README.md

@@ -355,6 +355,16 @@ It becomes `1girl, hatsune miku, vocaloid, microphone, stage, white shirt, best
 `1girl, hatsune miku, vocaloid, microphone, stage, white shirt, best quality, rating: general` や `1girl, hatsune miku, vocaloid, white shirt, smile, stage, microphone, best quality, rating: general` などになります。
 
 
+### Mar 15, 2024 / 2024/3/15: v0.8.5
+
+- Fixed a bug that the value of timestep embedding during SDXL training was incorrect.
+  - The inference with the generation script is also fixed.
+  - The impact is unknown, but please update for SDXL training.
+
+- SDXL 学習時の timestep embedding の値が誤っていたのを修正しました。
+  - 生成スクリプトでの推論時についてもあわせて修正しました。
+  - 影響の度合いは不明ですが、SDXL の学習時にはアップデートをお願いいたします。
+
 ### Feb 24, 2024 / 2024/2/24: v0.8.4
 
 - The log output has been improved. PR [#905](https://github.com/kohya-ss/sd-scripts/pull/905) Thanks to shirayu!

library/sdxl_original_unet.py

@@ -31,8 +31,10 @@ from torch import nn
 from torch.nn import functional as F
 from einops import rearrange
 from .utils import setup_logging
+
 setup_logging()
 import logging
+
 logger = logging.getLogger(__name__)
 
 IN_CHANNELS: int = 4
@@ -1074,7 +1076,7 @@ class SdxlUNet2DConditionModel(nn.Module):
         timesteps = timesteps.expand(x.shape[0])
 
         hs = []
-        t_emb = get_timestep_embedding(timesteps, self.model_channels)  # , repeat_only=False)
+        t_emb = get_timestep_embedding(timesteps, self.model_channels, downscale_freq_shift=0)  # , repeat_only=False)
         t_emb = t_emb.to(x.dtype)
         emb = self.time_embed(t_emb)
 
@@ -1132,7 +1134,7 @@ class InferSdxlUNet2DConditionModel:
     # call original model's methods
     def __getattr__(self, name):
         return getattr(self.delegate, name)
-    
+
     def __call__(self, *args, **kwargs):
         return self.delegate(*args, **kwargs)
 
@@ -1164,7 +1166,7 @@ class InferSdxlUNet2DConditionModel:
         timesteps = timesteps.expand(x.shape[0])
 
         hs = []
-        t_emb = get_timestep_embedding(timesteps, _self.model_channels)  # , repeat_only=False)
+        t_emb = get_timestep_embedding(timesteps, _self.model_channels, downscale_freq_shift=0)  # , repeat_only=False)
         t_emb = t_emb.to(x.dtype)
         emb = _self.time_embed(t_emb)