---
license: creativeml-openrail-m
---
# DeathNote Diffusion
<p>This is the fine-tuned Stable Diffusion model trained on images from the anime Death Note.<br/>
The following tokens will add their corresponding concept :<br/>
<ul>
	<li><b>DeathNote notebook</b> : the Deathnote itself</li>
	<li><b>Light Yagami</b> man : Light Yagami, main character</li>
	<li><b>Ryuk</b> demon : Ryuk, Shinigami</li>
	<li><b>LLawliet</b> man : L, "full" name</li>
	<li><b>Misa Amane</b> girl : Second Kira</li>
	<li><b>Soichiro Yagami</b> man : Soichiro, Father of Light, Policeman</li>
	<li><b>Sayou Yagami</b> girl : Sayou, sister of Light</li>
	<li><b>Raye Penber</b> man : Raye, FBI Agent</li>
	<li><b>Naomi Misora</b> girl : Naomi, fiance of Raye</li>
	<li><b>DNStyle style</b> : style of the anime</li>
</ul>

### 🧨 Diffusers

This model can be used just like any other Stable Diffusion model. For more information,
please have a look at the [Stable Diffusion](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion).

You can also export the model to [ONNX](https://huggingface.co/docs/diffusers/optimization/onnx), [MPS](https://huggingface.co/docs/diffusers/optimization/mps) and/or [FLAX/JAX]().

```python
from diffusers import StableDiffusionPipeline
import torch

model_id = "Guizmus/DeathNote"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")

prompt = "Ryuk demon, intricate, headshot, highly detailed"
image = pipe(prompt).images[0]

image.save("./Ryuk_demon.png")
```

## Examples

### DNSStyle, style of the anime

<p>
	<u>Sampling :</u> 30 k_Euler_a<br/>
	<u>CFGS :</u> 7 to 9, denoising 0.5<br/>
	<u>Prompts :</u><br/>
	<ul>
		<li>first txt2img : DNStyle style, anime girl sunbathing in a field</li>
		<li>second txt2img : </li>
		<li>img2img : DNStyle style, anime guy</li>
	</ul>
	<img src="https://huggingface.co/Guizmus/DeathNote/raw/main/samples/dnsstyle.jpg"/>
</p>