metadata

tags:
  - stable-diffusion-xl
  - stable-diffusion-xl-diffusers
  - text-to-image
  - diffusers
  - lora
  - template:sd-lora
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: Margiela SS24 style
license: openrail++

SDXL LoRA DreamBooth - tonyassi/mgm

by Tony Assi

Dreambooth style based on classic MGM Films. Try the demo.

Trigger words

Use mgm film in the prompt to trigger the MGM style.

How to use

pip install diffusers

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/mgm")
pipe.to("cuda")

# Generate image
prompt = "mgm film megan fox pinup girl"
image = pipe(prompt=prompt,
             height=1024, 
             width=1024,
             num_inference_steps=50,
             negative_prompt="ugly, deformed face, deformed body").images[0]
image