From 9a21b891533cb6c63ea82908384baaf052767ab7 Mon Sep 17 00:00:00 2001
From: ClashSAN <98228077+ClashSAN@users.noreply.github.com>
Date: Sun, 30 Jul 2023 06:10:18 -0400
Subject: [PATCH] Change VAE note to specify as the most up-to-date

---
 Features.md | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/Features.md b/Features.md
index 682b149..b54de47 100644
--- a/Features.md
+++ b/Features.md
@@ -16,7 +16,7 @@ All examples are non-cherrypicked unless specified otherwise.
 
 These models **specifically** are recommended for generating, merging and training.
 
->They have a built-in trained vae by [madebyollin](https://github.com/madebyollin) which fixes NaN infinity calculations running in fp16. ([VAE](https://huggingface.co/madebyollin/sdxl-vae-fp16-fix/blob/main/sdxl_vae.safetensors) for reference)
+>They have a built-in trained vae by [madebyollin](https://github.com/madebyollin) which fixes NaN infinity calculations running in fp16. (Here is the most up-to-date [VAE](https://huggingface.co/madebyollin/sdxl-vae-fp16-fix/blob/main/sdxl_vae.safetensors) for reference)
 
 ## SD-XL BASE
 
@@ -47,8 +47,6 @@ This secondary model is **designed** to process the `1024×1024` SD-XL image **n
 
 - [wcde/sd-webui-refiner](https://github.com/wcde/sd-webui-refiner) *To try this kind of generation, you can use this extension. 
 
->You will want 6gb minimum as `--lowvram` currently isn't supported.
-
 # SD2 Variation Models
 [PR](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/8958), ([more info.](https://github.com/Stability-AI/stablediffusion/blob/main/doc/UNCLIP.MD))