|
1 | | -# DreamBooth Hackathon |
| 1 | +# DreamBooth Hackathon 🏆 |
2 | 2 |
|
3 | | -Give instructions + rules + prizes |
| 3 | +Welcome to the DreamBooth Hackathon! This is a community event where you'll **personalise a Stable Diffusion model by fine-tuning it on a handful of your own images.** To do so, you'll use a powerful technique called [_DreamBooth_](https://arxiv.org/abs/2208.12242), which allows one to implant a subject (e.g. your pet or favourite dish) into the output domain of the model such that it can be synthesized with a _unique identifier_ in the prompt. |
4 | 4 |
|
5 | | -Dates: Jan 2 - 20, judges picks Jan 23 - 27 |
| 5 | +This competition is composed of 5 _themes_, where each theme will collect models belong to the following categories: |
6 | 6 |
|
7 | | -Register for Colab credits by December 31st |
| 7 | +* **Animal 🐨:** Use this theme to generate images of your pet or favourite animal hanging out in the Acropolis, swimming, or flying in space. |
| 8 | +* **Science 🔬:** Use this theme to generate cool synthetic images of galaxies, proteins, or any domain of the natural and medical sciences. |
| 9 | +* **Food 🍔:** Use this theme to tune Stable Diffusion on your favourite dish or cuisine. |
| 10 | +* **Landscape 🏔:** Use this theme to generate beautiful landscapes of your faourite mountain, lake, or garden. |
| 11 | +* **Wildcard 🔥:** Use this theme to go wild and create Stable Diffusion models for any category of your choosing! |
8 | 12 |
|
9 | | -Basic sketch: |
| 13 | +We'll be **giving out prizes to the top 3 most liked models per theme**, and you're encouraged to submit as many models as you want! |
10 | 14 |
|
11 | | -1. Join org on Hub |
12 | | -2. Submit models by theme |
13 | | -3. Ranked by likes (don't cheat!) |
| 15 | +## Getting started |
14 | 16 |
|
15 | | -Prizes: |
| 17 | +Follow the steps below to take part in this event: |
16 | 18 |
|
17 | | -- Copy of book |
18 | | -- Swag (ask merch?) |
19 | | -- Spaces w GPUs? |
| 19 | +1. Join the [Hugging Face Discord server](https://huggingface.co/join/discord) and check out the `#dreambooth-hackathon` channel to stay up to date with the event. |
| 20 | +2. Launch and run the [DreamBooth notebook](https://github.com/huggingface/diffusion-models-class/blob/main/hackathon/dreambooth.ipynb) to train your models by clicking on one of the links below. Make sure you select the GPU runtime in each platform to ensure your models train fast! |
| 21 | + |
| 22 | +| Notebook | Colab | Kaggle | Gradient | Studio Lab | |
| 23 | +|:--------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| |
| 24 | +| DreamBooth Training | [](https://colab.research.google.com/github/huggingface/diffusion-models-class/blob/main/hackathon/dreambooth.ipynb) | [](https://kaggle.com/kernels/welcome?src=https://github.com/huggingface/diffusion-models-class/blob/main/hackathon/dreambooth.ipynb) | [](https://console.paperspace.com/github/huggingface/diffusion-models-class/blob/main/hackathon/dreambooth.ipynb) | [](https://studiolab.sagemaker.aws/import/github/huggingface/diffusion-models-class/blob/main/hackathon/dreambooth.ipynb) | |
| 25 | + |
| 26 | +## Evaluation & Leaderboard |
| 27 | + |
| 28 | +To be in the running for the prizes, push one or more DreamBooth models to the Hub with the `dreambooth-hackathon` tag in the model card ([example](https://huggingface.co/lewtun/ccorgi-dog/blob/main/README.md#L9)). This is created automatically by the [DreamBooth notebook](https://github.com/huggingface/diffusion-models-class/blob/main/hackathon/dreambooth.ipynb), but you'll need to add it if you're running your own scripts. |
| 29 | + |
| 30 | +Models are evaluated according to the number of likes they have and you can track your model's ranking on the hackathon's leaderboard: |
| 31 | + |
| 32 | +* [DreamBooth Leaderboard](https://huggingface.co/spaces/dreambooth-hackathon/leaderboard) |
| 33 | + |
| 34 | +## Timeline |
| 35 | + |
| 36 | +* **December 21, 2022** - Start date |
| 37 | +* **December 31, 2022** - Colab Pro registration deadline |
| 38 | +* **January 22, 2023** - Final submissions deadline (closing of the leaderboard) |
| 39 | +* **January 23-27, 2023** - Announce winners of each theme |
| 40 | + |
| 41 | +All deadlines are at 11:59 PM UTC on the corresponding day unless otherwise noted. |
| 42 | + |
| 43 | +## Prizes |
| 44 | + |
| 45 | +We will be awarding 3 prizes per theme, where **winners are determined by the models with the most likes** on the leaderboard: |
| 46 | + |
| 47 | +**1st place winner** |
| 48 | + |
| 49 | +* [Hugging Face Pro subscription](https://huggingface.co/pricing) for 1 year or a $100 voucher for the [Hugging Face merch store](https://store.huggingface.co/) |
| 50 | + |
| 51 | +**2nd place winnner** |
| 52 | + |
| 53 | +* A copy of the [_NLP with Transformers_](https://transformersbook.com/) book or a $50 voucher for the [Hugging Face merch store](https://store.huggingface.co/) |
| 54 | + |
| 55 | +**3rd place winner** |
| 56 | + |
| 57 | +* [Hugging Face Pro subscription](https://huggingface.co/pricing) for 1 month or a $15 voucher for the [Hugging Face merch store](https://store.huggingface.co/) |
| 58 | + |
| 59 | + |
| 60 | +## Compute |
| 61 | + |
| 62 | +Google Colab will be sponsoring this event by providing Colab Pro credits to 100 participants (selected randomly). To register for these credits, fill out your details in this form. |
0 commit comments