AlekseyCalvin/Eszter_W_style_art_Ver2_Flux_LoRA_BySilverAgePoets

Eszter Winkelmayer Style Psychedelicate Art VERSION 2

HISTORIC 𝒜𝓡𝒯𝚒𝕤𝕥 STYLE ℒ𝓸ℜ𝐴𝘴

||| By SilverAgePoets.com |||

Second version of our Eszter Winkelmayer Art Style Low-Rank Adapter (LoRA) for FLUX-family models... <br> This Rank32 (32dim 64 alpha) variant was drawn from an expanded (from Version 1) manually-recaptioned/pre-processed dataset... <br> Trained over the De-distilled GENOVA_APEX Flux model by DNA_1_618 and the modified LongCLIP Text Encoder by zer0int (with the T.E. untrained for this variant). <br> The first version of this Eszter LoRA, tuned over vanilla FluxDev at Rank16, is found HERE! <br> The third variant of this LoRA (also Rank 32 dim & alpha) is found HERE, fine-tuned over Ablated/De-restricted Modification (v2) of FluxDev by aoxo and the modified LongCLIP Text Encoder by zer0int... <br> Fine-tuned on around 50 unforgettably self-singular ink illustrations – <br> ...each like a potent alchemical extract of a phenomenon or a concept, of an apparition or a dimension, carried thru under the easy law of a masterful hand...<br> Set to glue behind our eyes every cosmic topology and unreserved encapsulation spawned amid the limitless vision of their artist: <br> East Bay's own legendary reality-stylist (and up-and-coming attorney):<br> ESZTER WINKELMAYER!<br>

<Gallery />

Prompt with:

Eszter style psychedelicate illustration art, figuration distinctively stylized by Eszter Winkelmeyer, geometric patterns, ink, intricate linework, irreverent cosmic punk, mandala-like, hyper-structural neo-Symbolism, etc... <br>

A few of the original artworks by Eszter Winkelmayer used in our training data:<br>

[image] [image] [image] [image]

Use it with the 🧨 diffusers library

from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('AlekseyCalvin/Eszter_W_style_art_Ver2_Flux_LoRA_BySilverAgePoets')
image = pipeline('your prompt').images[0]