SDXL LoRA DreamBooth - comic_style_LoRA

Image 1	Image 2

Image 3	Image 4
---	---

Model description

These are comic_style LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.

The weights were trained using DreamBooth.

LoRA for the text encoder was enabled.

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

DataSet: custom hand-drawn sketches by ritwikraha

Trigger words

You should use a photo in the style of TOK comics to trigger the image generation.

Usage

!pip install diffusers accelerate -q
import torch
from PIL import Image
from diffusers import DiffusionPipeline, AutoencoderKL

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('ritwikraha/comics_style_LoRA')
_ = pipe.to("cuda")

prompt = "a photo of 18th century London in the style of TOK comics, 8k"
negative_prompt ="ugly face, multiple bodies, bad anatomy, disfigured, extra fingers"
image = pipe(prompt=prompt,
             negative_prompt=negative_prompt,
             guidance_scale=3,
             num_inference_steps=50).images[0]
image

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.