From d6e04180ffe34b9eb6011e434ad1afd23d99bd43 Mon Sep 17 00:00:00 2001 From: spawner Date: Sat, 7 Jun 2025 20:00:01 +0800 Subject: [PATCH] Update README.md --- README.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 978de83..e6f32b9 100644 --- a/README.md +++ b/README.md @@ -20,9 +20,10 @@ git clone https://github.com/spawner1145/CUI-Lumina2-TeaCache.git 4. Click `Install` # usage -![image](https://github.com/user-attachments/assets/e4fb8f9f-656e-49ce-9ef9-52827f728bdf) +![image](https://github.com/user-attachments/assets/fae7bebe-3af1-48f4-9a22-432bb6b9b4fa) 1. Connect the `TeaCache` node between the `UNet Loader` and `KSampler` in your workflow. 2. Set the `rel_l1_thresh` parameter to a value greater than 0. +3. to work on low steps, you can set the value below to `[393.76566581, -603.50993606, 209.10239044, -23.00726601, 0.86377344]` and a bit large `rel_l1_thresh` for more speed, and for higher steps, you can set the value below to `[225.7042019806413, -608.8453716535591, 304.1869942338369, 124.21267720116742, -1.4089066892956552]` and a `rel_l1_thresh`<1.1 to get better quality and more speed. **Note:** - Higher `rel_l1_thresh` values will improve generation efficiency (manifested as shorter generation times), at the cost of reduced image quality.