<ul><li>Images is generated on SDXL Lightning 4 steps. You should try it. Most "finetuned" models are just a joke.</li><li>1.0 Lightning trained on same dataset but on Dream Diffusion LIGHTNING XL &amp; SD. Unfortunately, it does not give any positive effects with lightning models but give an amazing additional effects with regular SDXL.</li></ul>It reduces/completely solves the problem of deformed eyes.Recommended strength 0.5-0.7Good for merging.trained on close-up photographs of babies, children, men and women, as well as collages made from these photographs. The collages were needed to teach it how to deal with small faces. And it's works.

Files with SHA256: 6e7c593b349bac9baa7867e910c13aa415ca8aee3bc9d78016494b08bec84d5b