---
title: README
emoji: 🏃
colorFrom: red
colorTo: yellow
sdk: static
pinned: false
---
<img src="https://github.com/dome272/Wuerstchen/assets/61938694/0617c863-165a-43ee-9303-2a17299a0cf9">
Welcome to <b>WARP</b>. This is our little organization for multimodal generative models focussing on the visual domain. We have been working with generative image models a lot and
will soon work on video models as well. Our main team consists of:

- [Pablo Pernias](https://github.com/pabloppp/)
- [Dominic Rampas](https://github.com/dome272)


Feel free to join our [Discord](https://discord.gg/BTUAzb8vFY) channel!

Models:
<details>
<summary>
  Paella
</summary>
  <img src="https://user-images.githubusercontent.com/61938694/231021615-38df0a0a-d97e-4f7a-99d9-99952357b4b1.png" width=1200>
  <ul>
    <li>A simple & straightforward text-conditional image generation model that works on quantized latents.</li>
    <li>More details can be found in the <a href="https://arxiv.org/abs/2211.07292v2">paper</a>, the <a href="https://laion.ai/blog/paella/">blog post</a> and the <a href="https://www.youtube.com/watch?v=zdE1I6kYKYc">YouTube video</a>.</li>
    <li>Only accessible through <a href="https://github.com/dome272/Paella">GitHub</a>.</li>
  </ul>
</details>

<details>
<summary>
  Würstchen
</summary>
  <ul>
    <li>An efficient text-to-image model to train and use for inference. Achieves competetive performance to state-of-the-art methods, while needing only a fraction of the compute.</li>
    <li>More details can be found in the <a href="https://arxiv.org/abs/2306.006372">paper</a>.</li>
    <li>Versions:</li>
    <ul>
      <li>v1: Only accessible through <a href="https://github.com/dome272/Wuerstchen/">GitHub</a>.</li>
      <li>v2: Accessible through <a href="https://github.com/dome272/Wuerstchen/">GitHub</a> and Diffusers</li>
    </ul>
  </ul>
</details>