From 5ef0baf5eaec7f21a1666af424405cbee19f3764 Mon Sep 17 00:00:00 2001
From: AUTOMATIC <16777216c@gmail.com>
Date: Tue, 4 Oct 2022 08:52:11 +0300
Subject: add support for gelbooru tags in filenames for textual inversion

---
 modules/textual_inversion/dataset.py | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

(limited to 'modules/textual_inversion/dataset.py')

diff --git a/modules/textual_inversion/dataset.py b/modules/textual_inversion/dataset.py
index e8394ff6..7c44ea5b 100644
--- a/modules/textual_inversion/dataset.py
+++ b/modules/textual_inversion/dataset.py
@@ -9,6 +9,9 @@ from torchvision import transforms
 import random
 import tqdm
 from modules import devices
+import re
+
+re_tag = re.compile(r"[a-zA-Z][_\w\d()]+")
 
 
 class PersonalizedBase(Dataset):
@@ -38,8 +41,8 @@ class PersonalizedBase(Dataset):
             image = image.resize((self.width, self.height), PIL.Image.BICUBIC)
 
             filename = os.path.basename(path)
-            filename_tokens = os.path.splitext(filename)[0].replace('_', '-').replace(' ', '-').split('-')
-            filename_tokens = [token for token in filename_tokens if token.isalpha()]
+            filename_tokens = os.path.splitext(filename)[0]
+            filename_tokens = re_tag.findall(filename_tokens)
 
             npimage = np.array(image).astype(np.uint8)
             npimage = (npimage / 127.5 - 1.0).astype(np.float32)
-- 
cgit v1.2.1