Update README.md

README.md

@@ -14,11 +14,11 @@ thumbnail: "https://cdn.discordapp.com/attachments/1020199895694589953/102020060
 
 # pony-diffusion-v3 - "kept you waiting huh" edition
 
-pony-diffusion is a latent text-to-image diffusion model that has been conditioned on high-quality pony and furry SFW and NSFW images through fine-tuning.
+pony-diffusion is a latent text-to-image diffusion model that has been conditioned on high-quality pony, furry and other non photorealistic SFW and NSFW images through fine-tuning.
 
-WARNING: Compared to v1 of this model, v2 is much more capable of producing NSFW content so it's recommended to use 'safe' tag in prompt in combination with negative prompt for image features you may want to suppress. v2 model also has a slight 3d bias so negative prompts like '3d' or 'sfm' should be used to better match v1 outputs.  
+WARNING: This model is capable of producing NSFW content so it's recommended to use 'safe' tag in prompt in combination with negative prompt for image features you may want to suppress.
 
-With special thanks to [Waifu-Diffusion](https://huggingface.co/hakurei/waifu-diffusion) for providing finetuning expertise and [Novel AI](https://novelai.net/) for providing necessary compute.
+With special thanks to [Waifu-Diffusion](https://huggingface.co/hakurei/waifu-diffusion) for providing finetuning expertise.
 
 [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1mSharzQFPD4mIUxNwBG7LCLAzGUS8Bmy?usp=sharing)
 
@@ -35,13 +35,11 @@ With special thanks to [Waifu-Diffusion](https://huggingface.co/hakurei/waifu-di
 
 [Original PyTorch Model Download Link](https://mega.nz/file/Va0Q0B4L#QAkbI2v0CnPkjMkK9IIJb2RZTegooQ8s6EpSm1S4CDk)
 
-[Real-ESRGAN Model finetuned on pony faces](https://mega.nz/folder/cPMlxBqT#aPKYrEfgA_lpPexr0UlQ6w)
-
 ## Model Description
 
-The model originally used for fine-tuning is an early finetuned checkpoint of [waifu-diffusion](https://huggingface.co/hakurei/waifu-diffusion) on top of [Stable Diffusion V1-4](https://huggingface.co/CompVis/stable-diffusion-v1-4), which is a latent image diffusion model trained on [LAION2B-en](https://huggingface.co/datasets/laion/laion2B-en).
+The model originally used for fine-tuning is [Stable Diffusion V1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5), which is a latent image diffusion model trained on [LAION2B-en](https://huggingface.co/datasets/laion/laion2B-en).
 
-This particular checkpoint has been fine-tuned with a learning rate of 5.0e-6 for 4 epochs on approximately 450k pony and furry text-image pairs (using tags from derpibooru and e621) which all have score greater than `250`.
+This particular checkpoint has been fine-tuned with a learning rate of 5.0e-6 for 20 epochs on approximately 1.7M pony, furry and other cartoon text-image pairs (using metadata from derpibooru, e621 and danbooru).
 
 ## License