diff --git a/CHANGELOG.md b/CHANGELOG.md
index 4ae7923a7..13ea2cc7b 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,20 +1,21 @@
 # Change Log for SD.Next
 
-## Update for 2026-05-11
+## Update for 2026-05-12
 
-### Highlights for 2026-05-11
+### Highlights for 2026-05-12
 
 *What's New?*
 - Image editing models now can work with multiple image inputs!
 - Six new models: *HiDream-O1 Image*, *JoyAI Image Edit*, *Step1X-Edit*, *VIBE Image Edit* and *UltraFlux*
 - Enhanced capabilities for *Anima*, *Ernie-Image*, *LTX*, *Flux.2* and *Chroma* models
+- Enhanced *LoRA* capabilities in many models
 - UI improvements accross the board: *Main panels*, *Gallery*, *Kanvas*, *Networks*, and more...
 
 For full details, see [ChangeLog](https://github.com/vladmandic/automatic/blob/master/CHANGELOG.md)  
 
 [ReadMe](https://github.com/vladmandic/automatic/blob/master/README.md) | [ChangeLog](https://github.com/vladmandic/automatic/blob/master/CHANGELOG.md) | [Docs](https://vladmandic.github.io/sdnext-docs/) | [WiKi](https://github.com/vladmandic/automatic/wiki) | [Discord](https://discord.com/invite/sd-next-federal-batch-inspectors-1101998836328697867) | [Sponsor](https://github.com/sponsors/vladmandic)  
 
-### Details for 2026-05-11
+### Details for 2026-05-12
 
 - **Models**
   - [HiDream-O1-Image](https://huggingface.co/HiDream-ai/HiDream-O1-Image) pixel-level unified transformer model support  
@@ -106,6 +107,7 @@ For full details, see [ChangeLog](https://github.com/vladmandic/automatic/blob/m
   - `gradio` preprocess exception handling
   - `ipadapters` with offloading
   - `kanvas` outpaint
+  - `network` preview handle invalid image
 
 ## Update for 2026-04-28
 
diff --git a/TODO.md b/TODO.md
index 0156448cb..e71721286 100644
--- a/TODO.md
+++ b/TODO.md
@@ -8,7 +8,9 @@
 - Control tab verify overrides handling, @vladmandic
 - Reimplement `llama` remover for Kanvas, @vladmandic
 - Implement [pruna](https://github.com/PrunaAI/pruna), @vladmandic
+- Change params to default, @vladmandic
 
+- Detailer postprocessing, @CalamitousFelicitousness
 - Cloud providers, @CalamitousFelicitousness
 - Video processing add full API support, @CalamitousFelicitousness
 
diff --git a/installer.py b/installer.py
index 201d35e5c..525cc4400 100644
--- a/installer.py
+++ b/installer.py
@@ -530,7 +530,7 @@ def check_transformers():
     else:
         # target_transformers = '4.57.6'
         target_transformers = None
-        target_tokenizers = '0.22.2'
+        target_tokenizers = '0.23.1'
     if target_transformers is not None:
         # Pinned release version (e.g. DirectML)
         if (pkg_transformers is None) or ((pkg_transformers.version != target_transformers) or (pkg_tokenizers is None) or ((pkg_tokenizers.version != target_tokenizers) and (not args.experimental))):
diff --git a/modules/styles.py b/modules/styles.py
index d263598dd..b25fcd91a 100644
--- a/modules/styles.py
+++ b/modules/styles.py
@@ -446,6 +446,8 @@ class StyleDatabase:
             log.error(f'Styles invalid: {p.styles}')
             return
         for style in p.styles:
+            if style is None or style == '':
+                continue
             s = self.find_style(style)
             if s == self.no_style:
                 log.warning(f'Apply style: name="{style}" not found')
diff --git a/modules/ui_extra_networks.py b/modules/ui_extra_networks.py
index 99b818f16..3c3bf2817 100644
--- a/modules/ui_extra_networks.py
+++ b/modules/ui_extra_networks.py
@@ -923,7 +923,10 @@ def create_ui(container, button_parent: gr.Button, tabname: str, skip_indexing =
                 b64str = ui.last_item.preview.split(',',1)[1]
                 img = Image.open(io.BytesIO(base64.b64decode(b64str)))
             elif hasattr(item, 'local_preview') and os.path.exists(item.local_preview):
-                img = item.local_preview
+                if os.path.getsize(item.local_preview) < 1024: # sanity check
+                    img = page.find_preview_file(item.filename)
+                else:
+                    img = item.local_preview
             else:
                 img = page.find_preview_file(item.filename)