diff --git a/CHANGELOG.md b/CHANGELOG.md
index e6315c466..133f6f523 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -20,6 +20,7 @@
   - lora: support diffusers trainer
   - load: flux1 t5
   - preview: cache image for reuse
+  - kanvas: fix paint combined with zoom
 
 ## Update for 2026-07-14
 
diff --git a/TODO.md b/TODO.md
index 57e2c4509..efd22462d 100644
--- a/TODO.md
+++ b/TODO.md
@@ -13,16 +13,18 @@
 - Cloud providers, @CalamitousFelicitousness
 - Video processing add/verify full API support, @CalamitousFelicitousness
 - Storage analyzer, @vladmandic
+- Lora: new handler, @CalamitousFelicitousness
+- Processing -> Video capabilities, @vladmandic
+  - `NudeNet` in processing
+  - `RIFE` in processing
+  - `SeedVR2` in processing
 
 ### Unassigned
 
 - [Nunchaku Lite](https://github.com/huggingface/diffusers/pull/14100)
-- Processing -> Video capabilities
-  - `RIFE` in processing
-  - `SeedVR2` in processing
 - [Object clear](https://huggingface.co/jixin0101/ObjectClear) remover for Kanvas
 - Video models: add to Reference
-- Video models: support custom entries
+- Video models: support custom entries, finetunes
 - UI Lite vs Expert mode
 - Auto handle scheduler `prediction_type`
 - Cache models in memory
diff --git a/extensions-builtin/sdnext-kanvas b/extensions-builtin/sdnext-kanvas
index 0261cc283..dc47fa212 160000
--- a/extensions-builtin/sdnext-kanvas
+++ b/extensions-builtin/sdnext-kanvas
@@ -1 +1 @@
-Subproject commit 0261cc2830326cf573222fb6ae8b9597a45e69cc
+Subproject commit dc47fa2129673caa69ffadeeffba49700e1a7d4a