This is my first ever LoRA trained on Tensor. The two LoRAs before this were original too, made by me, but they were imported from PixAI. This one was trained online here on Tensor.

It gave me the style I wanted and creates very detailed eyes, which was the main goal.

It works for both men and women. I recommend using the parameters that LoRA itself suggests when you set it up for generation.

Obviously, if you're a pro generator, you can do whatever you want.

𝐔𝐏𝐃𝐀𝐓𝐄𝐃 (𝐈𝐌𝐏𝐎𝐑𝐓𝐀𝐍𝐓 𝐓𝐎 𝐑𝐄𝐀𝐃):

I made a V2 that is way better than the V1. The eyes are detailed, the style is defined without copying the hair and the clothes of the original images... I think it's almost perfect. If you want to test this style, ignore the V1 and go directly to the V2. Works for males and females, but Danbooru is 98% females so the models will always struggle to generate males. Unfair, but with good promoting it can be solved. If the male pics come out ugly, use the Hi-Res with x1.5, 15 steps and. 3.5 of denoising. I recommend R-ESRGAN 4x+ Anime6B.

𝐔𝐏𝐃𝐀𝐓𝐄 𝟐:

Recommended weight: 0.6. Also, try to avoid generic prompts like "ultra detailed" or "high quality".

The E10 version is better for clothing and full body. The original (E14) is better for eyes and faces. 🩷

I would appreciate any advice, feedback, and for you to share your work. Thank you very much.