This is a custom LoRA model for the character INFP, also known as Mediator from the website 16 Personalities. I trained the model using 24 high-quality images and utilized the AbyssOrangeMix3 model. I manually removed each watermark from each image used in the training, then upscaled the images for the highest possible quality.

For optimal results, I recommend using the Euler a sampler, with the following recommended parameters:

• CFG scale of 7

• 20 steps

• hires upscaler set to Latent (nearest-exact)

• 20 hires steps

• Denoising strength of 0.52

For optimal performance, it is recommended that the weight of the LoRA be set within the range of 0.8-1.

To accurately depict an INFP's appearance, I suggest including green hair, green eyes, head wreath, and green dress in the positive prompt.

Please feel free to leave a comment below if you have any requests for LoRA models.