From acf81934c51abefaae1ca6d82db29f57222d8e33 Mon Sep 17 00:00:00 2001
From: Augusto de la Torre <tweaqslug@gmail.com>
Date: Thu, 12 Jan 2023 22:48:50 +0100
Subject: [PATCH] Update SD 1.5 training example to use --ed1_mode

---
 doc/TRAINING.md | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/doc/TRAINING.md b/doc/TRAINING.md
index aece041..89df00b 100644
--- a/doc/TRAINING.md
+++ b/doc/TRAINING.md
@@ -41,7 +41,8 @@ Resuming from a checkpoint, 50 epochs, 6 batch size, 3e-6 learning rate, cosine
     --sample_steps 200 ^
     --lr 3e-6 ^
     --ckpt_every_n_minutes 10 ^
-    --useadam8bit
+    --useadam8bit ^
+    --ed1_mode
 
 Training from SD2 512 base model, 18 epochs, 4 batch size, 1.2e-6 learning rate, constant LR, generate samples evern 100 steps, 30 minute checkpoint interval, adam8bit, using imagesin the x:\mydata folder, training at resolution class of 640: