Update README.md

README.md

@@ -16,7 +16,22 @@ tags:
 # Kawai Diffusion v4-nightly (≧∇≦)ﾉ
 See more in CivitAI : https://civitai.com/models/21138/kawai-diffusion-sd15
 ![](assets/preview.png)
+# What's new in Kawai v4-nightly:
+Why did I name this version "nightly"? Just a random choice. Besides, Kawai is always trained late at night when everyone is already asleep.
 
+The Nightly version allows you to use what we will do for the official LTS version.
+
+- Feature:
+
+- + The image quality has been significantly upgraded, thanks to a highly curated dataset.
+
+- + Use VAE of stabilityai: [stabilityai/sd-vae-ft-mse-original · Hugging Face](https://huggingface.co/stabilityai/sd-vae-ft-mse-original)
+
+- + True "kawaii"~~~
+
+- + Img2Img is extremely powerful.
+
+- + avatar: a new tag that allows you to create close-up images of a character's face. Suitable for use as a profile picture.
 ## Introduction:
 - It's an AI art model for converting text to images, images to images, inpainting, and outpainting using Stable Diffusion.
 - The AI art model is developed with a focus on the ability to draw anime characters relatively well through fine-tuning using Dreambooth.
@@ -66,6 +81,8 @@ Want to support me? Thank you, please help me make it better. ❤️
 ## Special Thank:
 This wouldn't have happened if they hadn't made a breakthrough.
 - [Runwayml](https://huggingface.co/runwayml/):  Base model.
+- [CompVis](https://github.com/CompVis/): VAE Trainer.
+- stabilityai: [stabilityai/sd-vae-ft-mse-original · Hugging Face](https://huggingface.co/stabilityai/sd-vae-ft-mse-original)
 - [d8ahazard](https://github.com/d8ahazard/.sd_dreambooth_extension) : Dreambooth.
 - [Automatic1111](https://github.com/AUTOMATIC1111/) : Web UI.
 - [Mikubill](https://github.com/Mikubill/): Where my ideas started.