Update README.md

README.md

@@ -2,7 +2,7 @@
 language:
 - en
 license: creativeml-openrail-m
-thumbnail: "https://huggingface.co/Guizmus/MosaicArt/resolve/main/showcase.png"
+thumbnail: "https://huggingface.co/Guizmus/MosaicArt/resolve/main/showcase.jpg"
 tags:
 - stable-diffusion
 - text-to-image
@@ -10,7 +10,9 @@ tags:
 ---
 # Mosaic Art
 
-![Showcase](https://huggingface.co/Guizmus/MosaicArt/resolve/main/showcase.png)
+## Details
+
+![Showcase](https://huggingface.co/Guizmus/MosaicArt/resolve/main/showcase.jpg)
 This is a Dreamboothed Stable Diffusion model trained on pictures of mosaic art.
 
 The total dataset is made of 46 pictures. V2 was trained on [Stable diffusion 2.1 768](https://huggingface.co/stabilityai/stable-diffusion-2-1). I used [StableTuner](https://github.com/devilismyfriend/StableTuner) to do the training, using full caption on the pictures with almost no recurring word outside the main concept, so that no additionnal regularisation was needed. 6 epochs of 40 repeats on LR 1e-6 were used, with prior preservation.
@@ -21,10 +23,18 @@ The token "Mosaic Art" will bring in the new concept, trained as a style.
 
 The recommended sampling is k_Euler_a or DPM++ 2M Karras on 20 steps, CFGS 7.5 .
 
+
+## Model v2
+
 [CKPT v2](https://huggingface.co/Guizmus/MosaicArt/resolve/main/MosaicArt_v2.ckpt)
 
 [YAML v2](https://huggingface.co/Guizmus/MosaicArt/resolve/main/MosaicArt_v2.yaml)
 
+
+## Model v1
+
+![Showcase](https://huggingface.co/Guizmus/MosaicArt/resolve/main/showcase.png)
+
 [CKPT v1](https://huggingface.co/Guizmus/MosaicArt/resolve/main/MosaicArt_v1.ckpt)
 
 [CKPT v1 with ema weights](https://huggingface.co/Guizmus/MosaicArt/resolve/main/MosaicArt_v1_ema.ckpt)