From ec7b0cf3d13fdf8dfa92d8928c6fdbbcac9ba630 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jukka=20Sepp=C3=A4nen?=
 <40791699+kijai@users.noreply.github.com>
Date: Wed, 23 Oct 2024 18:27:36 +0300
Subject: [PATCH] Update readme.md

---
 readme.md | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/readme.md b/readme.md
index 429b606..bf5a8fe 100644
--- a/readme.md
+++ b/readme.md
@@ -4,6 +4,9 @@
 # WORK IN PROGRESS
 
 ## Requires flash_attn !
+Not sure if this can be worked around, I compiled a wheel for my Windows setup (Python 3.12, torch 2.5.0+cu124) that worked for me:
+
+https://huggingface.co/Kijai/Mochi_preview_comfy/blob/main/flash_attn-2.6.3-cp312-torch250cu125-win_amd64.whl
 
 Depending on frame count can fit under 20GB, VAE decoding is heavy and there is experimental tiled decoder (taken from CogVideoX -diffusers code) which allows higher frame counts, so far highest I've done is 97 with the default tile size 2x2 grid.