Update README.md

README.md

@@ -8,6 +8,7 @@ tags:
 inference: true
 datasets:
 - Guizmus/AnimeChanStyle
+thumbnail: "https://huggingface.co/datasets/Guizmus/AnimeChanStyle/resolve/main/showcase_dataset.jpg"
 ---
 # 2D-Mix
 
@@ -29,4 +30,11 @@ Steps: 33, Sampler: Euler, CFG scale: 15, Seed: 4230961168, Size: 512x512, Model
 <img src=https://i.imgur.com/0foCNeo.png width=50% height=50%>
 woman in colorful kimono AND man in coloful yukata
 Negative prompt: gray, hazy, text, signature, cropped
-Steps: 33, Sampler: Euler, CFG scale: 15, Seed: 4230961169, Size: 512x512, Model hash: 63ac6702, Model: 2D-Mix, Clip skip: 5, ENSD: 31337
+Steps: 33, Sampler: Euler, CFG scale: 15, Seed: 4230961169, Size: 512x512, Model hash: 63ac6702, Model: 2D-Mix, Clip skip: 5, ENSD: 31337
+
+![showcase](https://huggingface.co/datasets/Guizmus/AnimeChanStyle/resolve/main/showcase_dataset.jpg)
+This is the dataset used for making the model  : https://huggingface.co/Guizmus/AnimeChanStyle
+The images were made by the users of Stable Diffusion discord using CreativeML-OpenRail-M licenced models, in the intent to make this dataset.
+90 pictures captioned with their content by hand, with the suffix ",AnimeChan Style"
+The collection process was made public during less than a day, until enough variety was introduced to train through a Dreambooth method a style corresponding to the different members of this community
+The picture captioned are available in [this zip file](https://huggingface.co/datasets/Guizmus/AnimeChanStyle/resolve/main/AnimeChanStyle%20v2.3.zip)