
Artist Style LoRA – Ekzonzz
Artist: Ekzonzz
LoRA Type: Artist Style
Trigger Word (v1): 3kz0nzz
Recommended Weight: 0.9–1.2 (ideal around 1.0)
Base Model: Illustrious v1.1
Overview
This LoRA is designed to capture the signature artistic look of Ekzonzz—a style defined by eerie and interesting crosshatching, outlining and abstract styles.
Training Information (v2)
Steps / Epochs: 3518 steps across 34 epochs
Clip Skip: 2
Dataset Size: 34
Optimizer: Adafactor / Cosine Res
Training was performed on Illustrious v1.1, so models within the Illustrious ecosystem pair most accurately with this LoRA.
Recommended Generation Settings
To get results that match the intended style:
Sampler: Euler_a
Steps: 30
CFG: 4.5
Positive Prompt Suggestions
These optional tags help guide the aesthetic:
Negative Prompt Suggestions
worst quality, lowres, bad anatomy, bad handsCompatibility
This LoRA works well with the following checkpoint:
WAI (Current Version): https://civarchive.com/models/827184/wai-illustrious-sdxl
Support the Artist
Please consider following or supporting Ekzonzz.
This LoRA was created to help their style reach new audiences across the AI art community.
Respect the original artist and credit them whenever appropriate.
Have a question or suggestion?
I can usually be reached on Discord at: piper260
Description
Dataset tag improvement
Dataset image compatibility, update, and improvement
This model allows for a higher range of variance to Ekzonzz's style. It captures more of the normal style, and less of a grit-like style.