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 Xi Zhang and is not intended to reproduce his original works.

Use Flux1.D combined with other models to create new styles of digital art expression.

Version Highlights

Model trained on civitai with 68 images.

Recommended resources : Fluxmania

Recommended settings : dpmpp_2m or heunpp2 / sgm_uniform / 25 steps / guidance : 3.5
Weighting : around 0.6

Creator Sponsors

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.

Xi Zhang is a Chinese concept artist and illustrator based in Shanghai. Known for his evocative digital paintings, he blends traditional aesthetics with futuristic and cinematic elements. His work often explores themes of emotion, identity, and surreal storytelling, making him a sought-after talent in the fields of concept art and visual development.

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.

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.

Previous
Smooth Embeddings - Smooth Negative NoobAI
Next
Supergirl Outfit (FLUX) - flux v1

Model Details

Model type

LORA

Base model

Flux.1 D

Model version

V1

Model hash

d874d7a952

Trained words

By Xi Zhang

Creator

Discussion

Please log in to leave a comment.