Update README.md

README.md

@@ -1,3 +1,26 @@
 ---
 license: cc-by-nc-4.0
+tags:
+- text-to-image
+- stable-diffusion-xl
 ---
+
+## Overview
+
+This is an anime-style Stable Diffusion XL model, trained using approximately 400 fixed art style images generated from NovelAI Diffusion Anime V3. It is developed through the [LyCORIS Native Fine-Tuning](https://github.com/KohakuBlueleaf/LyCORIS/blob/main/docs/Algo-List.md#native-fine-tuning) method, combined with the [animagine-xl-3.0-base](https://huggingface.co/cagliostrolab/animagine-xl-3.0-base) model, and further refined to produce the final model.
+
+## Usage Guidelines
+
+* You don't need any **quality tags** , just use 1girl and any other prompt
+* use negative prompts like: `watercolor, oil painting, deformed, disfigured, lowres, bad anatomy, bad hands, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts`
+* `cfg scale = 4, Sampler: Euler a, Steps: 28`
+
+## Multi Aspect Resolution
+
+This model supports generating images at the following dimensions:
+
+| Dimensions | Aspect Ratio |
+| ---------- | ------------ |
+| 1024 x 1024 | 1:1 Square |
+| 832 x 1216 | 13:19 |
+| 1344 x 768 | 7:4 Horizontal |