# Excited to submit workflow to the '23 DreamBooth Hackathon at huggingface – it uses Storj DCS

**URL:** <https://forum.storj.io/t/excited-to-submit-workflow-to-the-23-dreambooth-hackathon-at-huggingface-it-uses-storj-dcs/20842>\
**Category:** Projects & Stories\
**Created:** [December 30, 2022, 8:42am UTC](https://forum.storj.io/t/excited-to-submit-workflow-to-the-23-dreambooth-hackathon-at-huggingface-it-uses-storj-dcs/20842 "2022-12-30T08:42:14Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![keleffew](https://storj.bcdn.literatehosting.com/user_avatar/forum.storj.io/keleffew/32/7149_2.png) [@keleffew](https://forum.storj.io/u/keleffew)\
**Post date:** [December 30, 2022, 8:42am UTC](https://forum.storj.io/t/excited-to-submit-workflow-to-the-23-dreambooth-hackathon-at-huggingface-it-uses-storj-dcs/20842/1 "2022-12-30T08:42:14Z")

</div>

Excited to submit to the '23 DreamBooth Hackathon at huggingface

Stable diffusion is an extremely revolutionary and popular text-to-image foundation model used to generate realistic images.

> **[bethecloud/golf-course-generator · Hugging Face](https://huggingface.co/bethecloud/golf-course-generator)**
>
> We’re on a journey to advance and democratize artificial intelligence through open source and open science.

If you have a Hugging Face account - plz check out the link above and like it, would be awesome to win!

If you don’t have an account it is very quick to make one!

**About Stable Diffusion**

Stable diffusion is an extremely revolutionary and popular text-to-image foundation model used to generate realistic images. Applications like Lens.ai are generating millions of dollars a month acting as simple UX wrappers on top of Stable Diffusion, creating custom, guided, and fine-tuned output for users looking to create exciting and beautiful Avatars.

Stable Diffusion works by tokenizing english language words (using [CLIP](https://huggingface.co/docs/transformers/model_doc/clip)) and iteratively applying input weights to latent space, in a way that gradually bringing the output closer to the input prompt.

- A key benefit of stable diffusion is that it can be fine-tuned to generate high-quality images with a **simple** and **open-source** text2image model.

Applications like [http://Lens.ai](https://t.co/McTGfti8fc) are generating $$$ by simply acting as simple UX wrapper to facilitate the process of creating exciting and beautiful Avatars. Check out my Collab Notebook for a step-by-step process on fine-tuning here: [https://colab.research.google.com/drive/1EnqpDiKOVYhR0c6f4CgmDg2zqcbYZJpB#scrollTo=a22e8a3e-620e-4dff-8cea-3732003c17fa](https://t.co/Lnk0r6pgp2)

**From my example submission:**

For this hackathon submission, we have fine tuned a model to create _scenic landscapes of golf-courses, with historic and mythological buildings in the background._

It’s using a small 21 image dataset (that’s stored [on the decentralized edge, on Storj DCS](https://link.storjshare.io/s/juo7ynuvpe5svxj3hh454v6fnhba/golf-courses/), that’s used to fine-tune the underlying stable diffusion model.

Goal is to replicate this with much larger datasets and showcase the use case pattern for data training models (ie LAION-5B) in future.

[You can check out my submission/blog post here (on Mirror.xyz) as well!! : )](https://mirror.xyz/bitkevin.eth/rmqxOCzeefxu53TEBaFByyxNJ9ynOdJ_5CAVhUbuER8)

---

<div class="post-metadata">

**Author:** ![keleffew](https://storj.bcdn.literatehosting.com/user_avatar/forum.storj.io/keleffew/32/7149_2.png) [@keleffew](https://forum.storj.io/u/keleffew)\
**Post date:** [February 23, 2023, 11:44pm UTC](https://forum.storj.io/t/excited-to-submit-workflow-to-the-23-dreambooth-hackathon-at-huggingface-it-uses-storj-dcs/20842/2 "2023-02-23T23:44:04Z")

</div>

Small update to docs here as well: [How to use Storj with Hugging Face - Storj DCS Docs](https://docs.storj.io/dcs/how-tos/hugging-face)