---
license: apache-2.0
datasets:
- huggan/anime-faces
pipeline_tag: unconditional-image-generation
---

# TinyDiT

TinyDiT is an **85 million parameter unconditional image generation model** trained on **21,000+ anime face images**.

## Model Details

* **Model Name:** TinyDiT
* **Architecture:** Diffusion Transformer (DiT-inspired)
* **Parameters:** 85M
* **Task:** Unconditional Image Generation
* **Dataset Size:** 21,000+ anime face images
* **VAE:** Lightweight 13M parameter VAE
* **Generation Type:** Anime face generation from random noise (no text conditioning)
* **Image Size:** 64x64px
* **Github Repo:** https://github.com/Nitesh1405/TinyDiT/tree/main

## Dataset

TinyDiT was trained on a curated anime face dataset containing over 21k images.

**Dataset Repository:** `huggan/anime-faces`

## VAE

The model uses a compact **13M parameter Variational Autoencoder (VAE)** for latent-space encoding and decoding. 


## Example Generated Images

Below is a sample images generated by TinyDiT:

<p align="center" style="display: flex;">
  <img src="images/sample.webp" width="64"/>
  <img src="images/sample2.webp" width="64"/>
  <img src="images/sample3.webp" width="64"/>
  <img src="images/sample4.webp" width="64"/>
  <img src="images/sample5.webp" width="64"/>
  <img src="images/sample6.webp" width="64"/>
  <img src="images/sample7.webp" width="64"/>
  <img src="images/sample8.webp" width="64"/>
  <img src="images/sample9.webp" width="64"/>
  <img src="images/sample10.webp" width="64"/>
  <img src="images/sample11.webp" width="64"/>
</p>

<p align="center" style="display: flex;">
  <img src="images/sample22.webp" width="64"/>
  <img src="images/sample12.webp" width="64"/>
  <img src="images/sample13.webp" width="64"/>
  <img src="images/sample14.webp" width="64"/>
  <img src="images/sample15.webp" width="64"/>
  <img src="images/sample16.webp" width="64"/>
  <img src="images/sample17.webp" width="64"/>
  <img src="images/sample18.webp" width="64"/>
  <img src="images/sample19.webp" width="64"/>
  <img src="images/sample20.webp" width="64"/>
  <img src="images/sample21.webp" width="64"/>
</p>

## Usage

* **HuggingFace Space:** https://huggingface.co/spaces/nitesh501/TinyDiT

```bash
git clone https://github.com/Nitesh1405/TinyDiT.git && cd TinyDiT

pip install -r requirements.txt

python app.py
#the model will automatically download on first run if you have wget, if not you can download the model from https://huggingface.co/nitesh501/tinydit and place it in TinyDit Folder.
```


## Limitations

* Trained only on anime face data
* Unconditional generation only
* Limited diversity compared to larger diffusion models
* May occasionally generate blurry or distorted outputs


## Acknowledgements

Inspired by DiT architectures, latent diffusion models, and the open-source generative AI community.