This LORA model is trained on an image of a sanpaku eyes (small iris).<h3>V1.0</h3>The iris becomes smaller when the weight is increased. However, if the weight is raised too high, the image becomes rough. 1.2 or lower is better.The image of a boy has a smaller iris than that of a girl.Angry, surprised, wide-eyed prompts work better.For realistic checkpoints, an older, more realistic person is generated.<h3>V2.0</h3>In version 2, the training step was increased to generate more smaller iris while using the same input images.LoRA weights can now be used with a weight of 1.When adapted to realistic models, it produces younger person than version 1(why?).

sanpaku eyes

Increased the number of training repitisions from 2 to 5 and increased the number of steps from 1500 to 3750

Files with SHA256: 5405957fd6bc1d4c1132e596db39b195fceedd5e7e1dbbf0bbd9515660457139