the model was trained on the collected photos of Eugene's face from Instagram and Yandex images. It was important to find images without covering the face with anything, as well as with high-quality facial detail.
There were few suitable examples, so I had to manually upscale using the Codeformer and GFPGAN neural networks.
After that, I adjusted the saturation, white balance and brightness to one level among all the samples, of which there were 25 samples.
I created a model for a true aesthetes!
It is recommended to write the following tokens: evgeny-ponasenkov, greece, vegetation, intricate, sharp focus, official jacket, dslr, dark, sunglasses, 18's century, detailed.
Copy the prompt and parameters from the preview to this model — you will not lose.
It is best to use the Deliberate_v2 model, but you can combine this LoRA with other solutions focused on photorealism, model will work perfectly with them.