Update README.md

README.md

@@ -1,3 +1,13 @@
 ---
 license: openrail
 ---
+This is a dreambooth of Erika Furudo from the visual novel Umineko No Naku Koro Ni. It was trained on the in game sprites cropped to 768 resolution. 
+To summmon Erika you may use "furudo erika" and you may add "gothic dress", "wedding dress", "pirate hat", "pointing", "mad", "blushing", "insane expression",
+"holding gumtape", "holding scythe", afterwards for some interesting variations. These were the tokens that the model was trained on so it should yield more particular outcomes
+then prompting normally. 
+
+![grid-0155.jpg](https://s3.amazonaws.com/moonup/production/uploads/1671410696826-63602a9f3605bd411c18b4e0.jpeg)
+
+This example was prompted with the 2000 step model with the prompt of "masterpiece, best quality, 1girl, solo, erika furudo, gothic dress
+Negative prompt: lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name
+Steps: 18, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 1499559386, Size: 720x1280, Model hash: ee3a0775, Batch size: 6, Batch pos: 0, Denoising strength: 0.7, Clip skip: 2, First pass size: 0x0"