Artist Style LoRA – Flookz

Artist: Flookz
LoRA Type: Artist Style
Trigger Word: fl00kz
Recommended Weight: 0.9–1.2 (ideal around 1.0)
Base Model: Illustrious v1.1

This model, being a sketch-based style, might need a little bit of FDetailer because of the artifacting within the eyes during distant generations.

Training Information

• Steps / Epochs: 3120 steps across 40 epochs

• Clip Skip: 2

• Dataset Size: 35

• Optimizer: Adafactor / Cosine W/ Res

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:

masterpiece, best quality, newest, colored sketch

Negative Prompt Suggestions

(multiple views, multiple, comic, comic panel), worst quality, lowres, bad anatomy, bad hands

Compatibility

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 Flookz.
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