Upload README.md

README.md

@@ -2,14 +2,12 @@
 language:
 - en
 license: creativeml-openrail-m
-thumbnail: "https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/showcase.jpg"
+thumbnail: "https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/images/showcase_main.jpg"
 tags:
 - stable-diffusion
 - text-to-image
 - image-to-image
 library_name: "EveryDream"
-datasets:
-- Guizmus/AnimeChanStyle
 inference: false
 ---
 
@@ -20,56 +18,72 @@ This is a collection of models made from and for the users of the Stable Diffusi
 Those are mainly done through the use of EveryDream, and should result in a Mega Model towards the end for the datasets that are compatible. Some model like the Anime one require to stay on a different starting point, and may not get merged.
 
 
-## AnimeChan Style
 
-<p>
-	<img alt="Showcase" src="https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/images/showcase_AnimeChan.jpg"/><br/>
-	This model was based on <a href="https://huggingface.co/naclbit/trinart_stable_diffusion_v2">Trinart</a> model.<br/>
-	The dataset was a collaborative effort of the Stable Diffusion #anime channel, made of pictures from the users themselves using their different techniques.<br/>
-	100 total pictures in the dataset, 300 repeats total each, over 6 Epoch on LR1e-6.<br/>
-	This was trained using EveryDream with a full caption of all training pictures. The dataset can be found <a href="https://huggingface.co/datasets/Guizmus/AnimeChanStyle">here</a>.<br/>
-	<br/>
-	The style will be called by the use of the token <b>AnimeChan Style</b>.<br/>
-	<br/>
-	To access this model, you can download the CKPT file below, or use the <a href="https://huggingface.co/Guizmus/AnimeChanStyle/tree/main">diffusers</a>
-</p>
+# 3DChanStyle Style
 
-[current v2 download link](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/AnimeChanStyle-v2.ckpt)
 
-[dataset for the second version](https://huggingface.co/datasets/Guizmus/AnimeChanStyle)
+## Dataset & training
 
-### First version
+This model was based on [RunwayML SD 1.5](https://huggingface.co/runwayml/stable-diffusion-v1-5) model with updated VAE.
 
-![first version showcase](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/showcase.jpg)
+The dataset was a collaborative effort of the Stable Diffusion #3D channel, made of pictures from the users themselves using their different techniques.
 
-[first version download link](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/AnimeChanStyle_v1.ckpt)
+120 total pictures in the dataset, 500 repeats total each, over 10 Epoch on LR1e-6.
 
-[dataset for the first version](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/AnimeChan%20Style.zip)
+This was trained using EveryDream with a full caption of all training pictures.
 
-## 3DChanStyle Style
+The style will be called by the use of the token **3D Style**.
 
-<p>
-	<img alt="Showcase" src="https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/images/showcase_3DChanStyle.jpg"/><br/>
-	This model was based on <a href="https://huggingface.co/runwayml/stable-diffusion-v1-5">RunwayML SD 1.5</a> model with updated VAE.<br/>
-	The dataset was a collaborative effort of the Stable Diffusion #3D channel, made of pictures from the users themselves using their different techniques.<br/>
-	120 total pictures in the dataset, half of those regularisation, 500 repeats total each, over 10 Epoch on LR1e-6 total.<br/>
-	This was trained using EveryDream with a full caption of all training pictures. The dataset can be found <a href="https://huggingface.co/datasets/Guizmus/3DChanStyle">here</a>.<br/>
-	<br/>
-	The style will be called by the use of the token <b>3D Style</b>.<br/>
-	Other significant token : rick roll, fullbody shot, bad cosplay man.<br/>
-	<br/>
-	To access this model, you can download the CKPT file below.
-</p>
+Other significant tokens : rick roll, fullbody shot, bad cosplay man
+
+## Showcase & Downloads
+
+![Showcase](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/images/showcase_3DChanStyle-v1.jpg)
+
+[CKPT (2GB)](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/ckpt/3DStyle-v1.ckpt)
+
+[CKPT with training optimizers (11GB)](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/ckpt/3DStyle-v1_with_optimizers.ckpt)
+
+[Dataset](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/datasets/3DChanStyle-v1.zip)
+
+
+
+# AnimeChan Style
+
+## Dataset & training
+
+This model was based on [Trinart](https://huggingface.co/naclbit/trinart_stable_diffusion_v2) model.
+
+The dataset was a collaborative effort of the Stable Diffusion #anime channel, made of pictures from the users themselves using their different techniques.
+
+100 total pictures in the dataset, 300 repeats total each, over 6 Epoch on LR1e-6.
+
+This was trained using EveryDream with a full caption of all training pictures.
+
+The style will be called by the use of the token **AnimeChan Style**.
+
+## Downloads v2
+
+![Showcase](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/images/showcase_AnimeChan-v2.jpg)
+
+[CKPT (2GB)](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/ckpt/AnimeChanStyle-v2.ckpt)
+
+[Dataset](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/datasets/AnimeChanStyle-v2.zip)
+
+## Downloads v1
+
+![Showcase](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/images/showcase_AnimeChan-v1.jpg)
+
+[CKPT (2GB)](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/ckpt/AnimeChanStyle-v1.ckpt)
+
+[Dataset](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/datasets/AnimeChanStyle-v1.zip)
 
-[CKPT download link (2GB)](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/3DStyle-v1.ckpt)
 
-[CKPT with optimizers download link (11GB)](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/3DStyle-v1_with_optimizers.ckpt)
 
-[dataset](https://huggingface.co/datasets/Guizmus/3DChanStyle)
 
 # License
 
-This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage.
+These models are open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage.
 The CreativeML OpenRAIL License specifies: 
 
 1. You can't use the model to deliberately produce nor share illegal or harmful outputs or content