A Low-Rank Adapter (LoRA) for FLUX-family models...
Trained by us to approximate the unique singular ethereal aesthetics of a uniquely compelling Bay Area-based contemporary artist: Jacqueline Trosclair aka "Jax" aka "Starlic Jorca" and many further names besides.

Prompt using:

JAX style art, illustration, ink on paper, stylized distinctive figurative artwork featuring ... or JAX style art, oil paint on canvas, stylized distinctive painting featuring ... , etc...

Run this LoRA with an API using Replicate

import replicate

input = {
    "prompt": "JAX style art, illustration, ink on paper, stylized distinctive figurative artwork featuring  ",
    "lora_weights": "https://huggingface.co/AlekseyCalvin/JaxStyleArt_FluxLoRa_Var1_BySilverAgePoets/resolve/main/JaxStyleArt.safetensors"
}

output = replicate.run(
    "black-forest-labs/flux-dev-lora",
    input=input
)
for index, item in enumerate(output):
    with open(f"output_{index}.webp", "wb") as file:
        file.write(item.read())

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/JaxStyleArt_FluxLoRa_Var1_BySilverAgePoets', weight_name='JaxStyleArt.safetensors')
image = pipeline('JAX style art, illustration, ink on paper, stylized distinctive figurative artwork featuring  ').images[0]

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers

Training details

Steps: 1600
Learning rate: 0.0004
LoRA rank: 32
Optimizer: AdamW8bit

Contribute your own examples

You can use the community tab to add images that show off what you’ve made with this LoRA.