From 4dbba4d06d79a2ffe5aeee4b4d583b858e179872 Mon Sep 17 00:00:00 2001
From: kijai <40791699+kijai@users.noreply.github.com>
Date: Mon, 15 Dec 2025 17:35:48 +0200
Subject: [PATCH] Update readme.md

---
 readme.md | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/readme.md b/readme.md
index 42be28b..018c294 100644
--- a/readme.md
+++ b/readme.md
@@ -1,5 +1,11 @@
 # ComfyUI wrapper nodes for [WanVideo](https://github.com/Wan-Video/Wan2.1) and related models.
 
+
+## Memory use update (again)
+
+I've made everythign less reliant on torch.compile for VRAM efficiency, so things should work better even without it. Also figured workaround for some issues when using compile that made first run use drastically more VRAM, issue I battled with myself a lot.
+
+
 ## Update notification that can affect memory use in old workflows
 
 In a recent update I changed how unmerged LoRA weights are handled:
@@ -108,6 +114,12 @@ Training free techniques:
 
 TimeToMove: https://github.com/time-to-move/TTM
 
+SteadyDancer: https://github.com/MCG-NJU/SteadyDancer
+
+One-to-all-Animation: https://github.com/ssj9596/One-to-All-Animation
+
+SCAIL: https://github.com/zai-org/SCAIL
+
 
 Not exactly Wan model, but close enough to work with the code base: