---
license: cc-by-2.0
library_name: diffusers
tags:
- art
- code
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
---
# SDXL LoRA DreamBooth - comic_style_LoRA

<Gallery />

| Image 1 | Image 2 |
|---|---|
| ![example 1](./1.png) | ![example 2](./2.png) |
| Image 3 | Image 4 |
|---|---|
| ![example 3](./3.png) | ![sample 4](./4.png) |


## Model description

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

The weights were trained  using [DreamBooth](https://dreambooth.github.io/).

LoRA for the text encoder was enabled.

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

DataSet: custom hand-drawn sketches by [ritwikraha](https://www.ritwikraha.com/)

## 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](ritwikraha/comics_style_LoRA/tree/main) them in the Files & versions tab.




---