A futuristic industrial landscape at sunset with tall buildings, cranes, machinery, a tank partially obscured by thick smog, and an illuminated streetlight in the foreground.
A high-contrast black and white abstract portrait where a person's silhouette is formed by a hyper-detailed Sumi-e ink splatter radiating from the head and shoulders.
A dimly lit futuristic cityscape at night featuring a lone person in a brown jacket looking out over a narrow canal surrounded by dilapidated brick buildings with neon signs and cyberpunk elements.
Three skeletal figures standing in a dimly lit, ruined gothic cathedral with tall ornate stone columns and fog surrounding them, creating a dark and eerie atmosphere.

Recommended Parameters

samplers

dpmpp_2m_sgm_uniform

steps

25

resolution

896x1152

vae

ae.sft

other models

Fluxmania V5P.safetensors (8ae0583b06)

Tips

Use the Flux1.D model in combination with other models to create new digital art styles.

Refer to the licensing conditions of the Flux Dev model on HuggingFace before use.

Version Highlights

Model trained on civitai with 64 images.

Recommended resources : Fluxmania

Recommended settings : dpmpp_2m or heunpp2 / sgm_uniform / 25 steps / guidance : 2.5 to 3.5
Weighting : around 0.7

Creator Sponsors

Arthur Yuan is a talented Chinese illustrator and concept artist known for his captivating and imaginative artwork.

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.

The idea is to use this model, combined with others, to create new styles of digital art expression. "Nothing is lost, nothing is created, everything is transformed" is an apocryphal quote from Antoine Lavoisier. We are somewhat in this vision.

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
Hassaku XL (Illustrious) - v1.2 - Style
Next
Hyper Realism Lora by aidma [FLUX + ILLUSTRIOUS] - FLUX v0.3

Model Details

Model type

LORA

Base model

Flux.1 D

Model version

V1

Model hash

21257e9ca9

Trained words

By Arthur Yuan

Creator

Discussion

Please log in to leave a comment.

Images by Arthur Yuan - V1

fantasy Images

sci-fi Images

style Images