Update README.md

README.md

@@ -13,13 +13,9 @@ tags:
 - stable diffusion
 ---
 
-# Kawai Diffusion (anime-base) v3.1 (≧∇≦)ﾉ
+# Kawai Diffusion v4-nightly (≧∇≦)ﾉ
 See more in CivitAI : https://civitai.com/models/21138/kawai-diffusion-sd15
 ![](asset/preview.png)
-## What's new in Kawai v3.1:
-- Inherit the best part of the deleted old Kawai v3.0 LTS version, add a little "grapefruit", avoid "grapefruit" too small. I don't want it to be deleted again because of the "airport". :v
-
-- Holy "kawaii desu~"
 
 ## Introduction:
 - It's an AI art model for converting text to images, images to images, inpainting, and outpainting using Stable Diffusion.
@@ -52,21 +48,6 @@ Read the following instructions, and if you understand, say "I understand": Comm
 - You should use it as a supportive tool for creating works of art, and not rely on it completely.
 - The Clip skip should be 2.
 
-## **Training**:
-- **Data**: Created by another AI.
-- **Schedule**: DDIM.
-- **Optimizer**: AdamW.
-- **Precision**: FP32.
-- **Hardware**: Google Colaboratory Pro - NVIDIA A100 40GB VRAM, TESLA V100-SXM2 16GB.
-## **Model Unit Test:**
-This is a program written by my friend to check model quality.
-- Examiner: OpenAI ChatGPT-3.5-Turbo.
-- Test: kawai-anime-sd.
-- Schedule: DPM++ 2M Karras.
-- Steps: 22.
-- Guard: Guard Prompt 1.5.
-- Test Report: [Here](https://civitai.com/gallery/299771?modelId=21138&modelVersionId=27219&infinite=false&returnUrl=%2Fmodels%2F21138%2Fkawai-diffusion-sd15).
-
 ## **Limitations:**
 - The drawing is hard, not soft.
 - Loss of detail, errors, bad human-like (six-fingered hand) details, deformation, blurring, and unclear images are inevitable.