From 952f9ce7be6794a88b12ba8fa37418c37b24f30a Mon Sep 17 00:00:00 2001
From: "Kohya S." <52813779+kohya-ss@users.noreply.github.com>
Date: Thu, 4 Sep 2025 19:46:04 +0900
Subject: [PATCH] Update docs/train_textual_inversion.md

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
---
 docs/train_textual_inversion.md | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/docs/train_textual_inversion.md b/docs/train_textual_inversion.md
index c18c2307..b7c69eb7 100644
--- a/docs/train_textual_inversion.md
+++ b/docs/train_textual_inversion.md
@@ -268,10 +268,7 @@ In your prompts, simply use the token string you trained (e.g., "mychar") and th
    * Try adjusting the learning rate (lower values like 5e-7)
    * Increase the number of training steps
 
-3. **Out of memory errors**
-   * Reduce batch size in the dataset configuration
-   * Use `--gradient_checkpointing`
-   * Use `--cache_latents` (for SDXL)
+   * Use `--cache_latents`
 
 <details>
 <summary>日本語</summary>