README.md

---
license: mit
tags:
- pytorch
- diffusers
- unconditional-image-generation
- diffusion-models-class
datasets:
- huggan/selfie2anime
---

# This model is a fine-tuned diffusion model for unconditional image generation of animefaces. 

Even after fine-tuning the diffusion model for 10 epochs the generated images are still cursed... 💀. Maybe more epochs would help?
![epoch10](dm_anime_epoch10.png)

## Usage

```python
from diffusers import DDPMPipeline

pipeline = DDPMPipeline.from_pretrained('Pie31415/dm_anime')
image = pipeline().images[0]
image
```