Low-polygon minimalist illustration of Batman with a black mask and cape, set against a blue background with raindrops and dramatic lighting.
A wizard glowing with magical light from his eyes in a flowing red cloak faces a small black cat with bright green eyes on a dark background.
Low-polygon style digital portrait of a demoness sorceress looking upward with glowing red eyes and backward curling horns, fiery amber and dark black background.

Recommended Parameters

samplers

dpmpp_2m_sgm_uniform

steps

25

resolution

896x1152

vae

ae.sft

other models

Fluxmania V6I_fp8.safetensors (d94dd45c94)

Tips

This model is a tribute to the artist and not an attempt to copy or reproduce his works.

Showcase images were created with ComfyUI and include metadata & workflow.

All licensing conditions for the Flux Dev model apply, details available on Huggingface.

Version Highlights

Model trained on civitai with 71 images.

Recommended resources : Fluxmania

Recommended inference : dtype E4M3 / dpmpp_2m or heunpp2 / sgm_uniform / 25 steps / guidance : 3.5
Weighting : around 1.0 (0.8 to 1.1)

Creator Sponsors

🎨 Liam Brazier is a UK-based illustrator and animator known for his bold, geometric style often described as “low poly art.”

🎨 Liam Brazier is a UK-based illustrator and animator known for his bold, geometric style often described as “low poly art.” Using vibrant colors and angular shapes, he deconstructs familiar figures and scenes into striking visual compositions. His work spans both still images and animation, blending pop culture references with a unique visual language.

He has collaborated with major clients such as Disney, the BBC, Netflix, Samsung, and Queens of the Stone Age, and his art has been featured in galleries across Europe and the US. Whether designing posters, animations, or editorial illustrations, Brazier brings a playful yet precise aesthetic that stands out in contemporary visual storytelling.

IMPORTANT NOTE: This model is a tribute to the artist and not an attempt to copy or reproduce his works. Flux1.D is unable to reproduce a graphic universe on which it was trained, the goal is solely to expand Flux's pictorial capabilities.

Showcase images were created with ComfyUI and are in PNG, include metadata & workflow.
All licensing conditions for the Flux Dev model apply. You can find the details
here.

Previous
DoubleExposure (SDXL+ PONY) - PONY
Next
China-Splashed Ink - v1.0

Model Details

Model type

LORA

Base model

Flux.1 D

Model version

V1

Model hash

6b0a3658ff

Trained words

LiaBraz style
A low polygonal illustration

Creator

Discussion

Please log in to leave a comment.

Images by Liam Brazier - V1

illustration Images

style Images