---
license: creativeml-openrail-m
---

This is a fine-tuned Stable Diffusion model (v1.5) trained on images (that I find aesthetically appealing) from various fantasy concept illustrators and designers (mostly Japanese, South Korean, or Chinese). Use the tokens **DBfantasyart style** in your prompts for the effect.

Download the checkpoint file (.ckpt) to use it.

If you want to **reproduce** the images below, I've prepared a more detailed version of the prompt settings and seed values in this **pastebin**: https://pastebin.com/2XrkSMfV

Example settings: Steps: 50, Sampler: Euler, CFG scale: 7, Size: 512x512

Example prompt: **DBfantasyart style**, masterpiece, 1girl, beautiful female portrait of sorceress

Some example images in txt2img (**very minimal editing/cleanup**):

![Fantasy Art Style](https://huggingface.co/kasukanra/fantasy-art-style/resolve/main/fantasyart_style_01.png)

![Fantasy Art Style](https://huggingface.co/kasukanra/fantasy-art-style/resolve/main/fantasyart_style_02.png)

![Fantasy Art Style](https://huggingface.co/kasukanra/fantasy-art-style/resolve/main/fantasyart_style_03.png)