Version 4 is for SDXL, for SD 1.5 version please pick version 1,2,3
I don't know a good prompt for this model, feel free to experiment
i also have a lora sdxl for this model
https://civarchive.com/models/121932/samaritan-3d-cartoon-sdxl
For SD 1.5 version make sure to use hi res fix and use a decent VAE or the color will become pale and washed out
if you like the models, please consider supporting me on, i will continue to upload more cool stuffs in the future
patreon.com/PromptSharingSamaritan
https://ko-fi.com/promptsharingsamaritan
Description
This update is a huge improvement ,less overtrained and the lora works better
I Use hires. fix, upscale latent, denoising 0.5, hires steps 20, upscale by 2 . Clip skip 2 .
I use night sky yozora VAE in the examples https://civitai.com/api/download/models/14459?type=VAE
if you like the models, please consider supporting me on, i will continue to upload more cool stuffs in the future
patreon.com/PromptSharingSamaritan
https://ko-fi.com/promptsharingsamaritan
IF YOU'RE NEW HERE
U need to use a proper VAE or the color become pale, and it will look way better if you use hi-res fix
copy the yozora VAE to stable-diffusion-webui-master\models\VAE and then go to automatic1111 webui , click on settings tab, the go to stable diffusion tab to the left, then go to SD VAE to select which VAE u want and then click apply settings.
FAQ
Comments (3)
Notice: Euler A sampler works significantly better than others
Love the model! I made a chart for people to look at that compares the 3 samplers I found worked the best, as well as various CFG and Step count settings. You can see it on my profile, if the author of model would like to post it themselves please feel free.
pruned 2Gb version plz