Jay Naylor style [Z-Image Turbo]
LORA
ZImageBase
LORA
ZImageBase
v1.0

Jay Naylor style [Z-Image Turbo]

desm0nt
Creator
⭐ 0.0
⬇ 206 Downloads
👁 1 Views
🖼 15 Images

About this model

WARNING! READ THIS!! PLEASE.

First, I hope furry fans have a good day. Second, V1.0 is trained on Z-image Base, but tested only on Turbo! For Turbo it needs Strengh 1.9 instead of 1. You must use strenght in the range of 1.6-1.9, as this is the most optimal range according to test results, where there is already style, but it does not draw dog noses on non-furry characters.
For other info read below please.

Model Info:

Jay Naylor art style for Z-Image Turbo.

Trained on 307 images.
Triggered by "art by jaynaylor, jaynaylor style". Strengh 0.9-1.1
(For Zi-base trained - 1.9!!)


UPDATE:

v1.0 is based on Base instead of Turbo. Overall, it follows the style much more accurately and has far fewer artifacts or broken anatomy. However, it has a number of compromises:

1) Requires a strength of 1.7-1.9 to produce a visible result.

2) Tends to make even regular humans furry - adding fur and animal noses.
3) Can a little bit of female "anatomy" but don't expect anything significant in this.


OLD v0.1: Due to the lack of a full model, training was performed on distillation, resulting in occasional anatomical distortions. Will be retrained after full model release.

Usage Recomendation:

IMPORTANT: always include prompts like Anime-style drawing or something similar. Z-Image Turbo STRONGLY leans towards photorealism, and unless explicitly instructed to create drawn graphics, it will produce photos or 3D CGI!

Author notes:

1) Please use with respect and support original artist because it's a very talented person.

2) If you want to support me - like, upload your pictures or generate with site generator, cause it give me both motivation and buzz for new Lora.

Related Models

Similar AI models you may like