readme

README.md

@@ -15,12 +15,24 @@ pipeline_tag: text-to-image
 
 ## Model Details
 
-ColorfulXL merged with lightning loras (2,8 steps) from bytedance, for fast inference (3-6 steps). 
+v1.6. Based on ColorfulXL, with lightning ability. 
+
+ - Fine-tuned on aesthetics
+ - Unet trained from 512 to 1280 with 64 steps
+ - Good prompt follow, trained text encoder
+ - Custom VAE
+ - Merged with 2,4,8, steps lightning unets from bytedance (supermario)
+ - Merged back with base model (not SGMUniform Euler works)
+ - Use with zero/low cfg
+ - Custom VAE
+ - Ability to generate pure white/black - colorful model with true colors
 
 High range of resolutions supported (576 - 1280), 576*832 example:
 
 ![steps](5.png)
 
+Black and white 
+
 It also works at huge resolutions like 1248 * 1824 (with Kohya HRFix Integrated)
 ![huge](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/7d8d701e-1346-460c-aa11-660b755a5a98/original=true/00055-3393169269.jpeg)
 params: https://civitai.com/images/9415168)