Update README.md

README.md

@@ -19,23 +19,20 @@ A SDXL anime base model aims to create unique artworks.
 
 ## Introduction
 
-This model can be seen as a derivative of Animagine XL 3.0 project.
-Basically I'm collaborating with Linaqruf for making better Anime base model (and it is obvious that we have different goal/target)
-We share our models and technique to improve our models' quality.
-And that is also how this model been created.
+This model can be seen as a derivative of Animagine XL 3.0 project.<br>
+Basically I'm collaborating with Linaqruf for making better Anime base model (and it is obvious that we have different goal/target)<br>
+We share our models and technique to improve our models' quality.<br>
+And that is also how this model been created.<br>
 
 
 ### Base7
 
 Kohaku-XL base7 is resumed from beta7 and use same dataset that beta series have used. But this time I use my own metadata system to create captions. (Can be taken as advanced version of what linaqruf used, will open source it soon)
 
-The metadata database can be downloaded here:
-KBlueLeaf/danbooru2023-sqlite · Datasets at Hugging Face
-
-Trainin details:
-LR: 8e-6/2e-6
-Scheduler: constant with warmup
-Batch size: 128 (batch size 4 * grad acc 16 * gpu count 2) 
+Trainin details:<br>
+LR: 8e-6/2e-6<br>
+Scheduler: constant with warmup<br>
+Batch size: 128 (batch size 4 * grad acc 16 * gpu count 2) <br>
 
 
 ### Gamma rev1
@@ -49,13 +46,13 @@ gamma rev1 = beta7 + 0.8 * (anxl3 - anxl2) + 0.5 * (base7 - beta7)
 ## Usage
 #### Parameter
 
-This model is trained under 768x1024 to 1024x1024 ARB. It is recommended to use pixel count within 786432 ~ 1310720.
-Recommended CFG scale is 4~7.
-Sampler should not matter.
+This model is trained under 768x1024 to 1024x1024 ARB. It is recommended to use pixel count within 786432 ~ 1310720.<br>
+Recommended CFG scale is 4~7.<br>
+Sampler should not matter.<br>
 
 #### Tagging
-This model use my own system for quality tags or something like that. 
-So although this model combine the diff weight from anxl3, I will still recommend user to use mine (or both) tagging system.
+This model use my own system for quality tags or something like that. <br>
+So although this model combine the diff weight from anxl3, I will still recommend user to use mine (or both) tagging system.<br>
 
 The format of prompt is as same as anxl3. (You can check the sample images I post)
 
@@ -83,8 +80,8 @@ Year tags (New to Old):
 * old
 
 
-You may meet some subtle mosaic-like artifact, that may be caused by high-lr or bad resizing/image encoding.
-I will try to fix it in next version. For now, try to use R-ESRGAN anime6b or SCUNet models for fixing it.
+You may meet some subtle mosaic-like artifact, that may be caused by high-lr or bad resizing/image encoding.<br>
+I will try to fix it in next version. For now, try to use R-ESRGAN anime6b or SCUNet models for fixing it.<br>
 
 ---