Arbuzbudesh Style Furry LoRA (Anthro)
Details
Download Files
About this version
Model description
ArbuzBudesh Style LoRA
Support ArbuzBudesh here:
Read The Price Of Freedom here:
https://priceforfreedom.net/comic/price_for_freedom/1
Get the game here:
Disclaimer and Request
Always credit ArbuzBudesh when posting images generated with this LoRA.
Trained on 100% publicly available images taken from e621.
Please do not sell this LoRA, or images generated with this LoRA (additionally, do not sell access to this LoRA, or access to images generated with this LoRA, e.g. via Patreon or other paid/subscription services).
Please do not remove metadata from images generated with this LoRA.
Model Info
Trained on: CoffeeNSFW (My fav. anime model)
Epoch: 10
Repeats: 5
Resolution: 640
Images: 470 from e621
I specifically filtered out images with the following tags:
video
animated
filetype:gif
date: older than 01/01/2016
lowres
Steps: 23500
ClipSkip: 2
Recommendations
Trigger Words: None needed
Weight: Around 0.9 yielded good results
Samplers:
Euler A showed surprisingly strong
Otherwise DPM++ 2M Karras was my go-to
Base Resolutions: Around 384x576
Upscalers:
4x_fatal_Anime_500000_G showed the best results
4x_fooldhardy_Remacri also did OK, but more washed out
Latent (nearest-exact) is also an OK option, but only at very high denoise
Extensions:
- Use Dynamic Thresholding Extension to use high CFGs without burn-in













