Lora: 0.70-0.85
If you want to create less erotic images, it would be advisable to use a checkpoint with support for generating adult-friendly images. It may seem silly, but that's how it works: otherwise, the checkpoint won't be able to recognize the tags used in training and will tend to include erotic elements in your drawing. I say this because the checkpoint used in the model doesn't understand that it's an adult-oriented image. If you decide to merge this model to have supornt from ault friendly, I recommend using "anything" the colection at 0.15 and 0.50 for this base model. Apart from that, enjoy using Lora!
If the number of images trained is low, use a checkpoint that influences interactions and not so much in style as this one. So you will have more varied images. Another option is to force it with prompts, so the matter is not so dramatic.
~~~~~~~
Hello everyone!
This is Tomas Agilar speaking, and I'm thrilled to have the opportunity to share my work and passion with all of you. If you enjoy what I do and would like to support me, there are a few ways you can do so:
Ko-fi (Dead)
Every donation, whether it's through Ko-fi or my Patreon membership, has a significant impact on my ability to keep creating and sharing content that you love. You are an essential part of my creative journey, and your support fuels me to reach new heights.
From the bottom of my heart, I want to thank you for considering supporting me. Every act of generosity inspires me and gives me the confidence to keep pursuing my dreams and projects. I encourage you to explore the provided links to learn more about my work and find a way to contribute.
Thank you for being here and for being a part of my community. Together, we can make a difference and achieve wonderful things. Have an amazing day!
With gratitude, Tomas Agilar