This version 2.0 contains an important update regarding the total removal of any watermark in the images, including the addition of new images totaling 975 images trained in Civitai, as I was dissatisfied with the results of version 1.0 which had some type of error due to to inappropriate settings in the LoRA training process

1) Always use the tag mariart, by mariart and/or omari, by omari

2) This LoRA is based on the Pony V6 model

3) Now the use of tags is up to you, if you are going to use a Pony model, don't forget the following basic tags:

score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up,

4) LoRA weight change in Civitai is at your discretion

Below is an initial configuration, but any other type of configuration is up to you:

Model

Incursio's Meme Diffusion (SDXL, Pony) /// In my tests, this model is closer to the author's style.

LoRA

MariArt (Omari) Style Lora v2.0 - 0.5 ~ 1.00

Advanced

CFG Scale - 7.0 ~ 9.0

Sampler - Euler a / DPM++ 2M Karras

Steps - 24 ~ 50

Clip Skip - 2

VAE - none

Prompt (Positive) (Pony Model)

score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, gray background, mariart, by mariart, anthro, furry, female, solo focus, horse, hair, curvy figure, casual clothing, dynamic pose

Prompt (Negative) (Pony Model)

zPDXL-neg, 3D

General Observations:

If possible, give credit to the author MariArt while using this LoRA.
Do not sell or commercialize this LoRA, if possible, help the author of the images through your Patreon.
Do not remove metadata from images generated by LoRA.

Support the artist using these links:

https://www.patreon.com/MariArt

https://www.furaffinity.net/user/omari/

https://www.mariart.info/

https://twitter.com/PwnPony