SDXL LoRA - tonyassi/warhol-lora

by Tony Assi

Lora style based on Andy Warhol prints.

Trigger words

Use Warhol style in the prompt to trigger the style.

How to use

pip install diffusers accelerate

import torch
from diffusers import DiffusionPipeline, AutoencoderKL

# Load the pipeline
vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
pipe = DiffusionPipeline.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0",
    vae=vae,
    torch_dtype=torch.float16,
    variant="fp16",
    use_safetensors=True
)
pipe.load_lora_weights("tonyassi/warhol-lora")
pipe.to("cuda")

# Generate image
prompt = "Warhol style, Bella Hadid"
image = pipe(prompt=prompt,
             height=1024, 
             width=1024,
             num_inference_steps=50,
             negative_prompt="ugly, deformed face, deformed body").images[0]
image

Examples

Warhol style, Bella Hadid

Warhol style, Lady Gaga

Warhol style, Nicole Kidman

Warhol style, A$AP Rocky

Warhol style, Scarlett Johansson

Warhol style, David Bowie

Model description

These are tonyassi/warhol-lora LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.

The weights were trained using DreamBooth.

LoRA for the text encoder was enabled: False.

Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.