# DiffusionBee

{% hint style="info" %}
[**dreamlook.ai**](https://dreamlook.ai/) **lets you finetune Stable Diffusion models in minutes (first run is free!)**\
Follow this guide to train models on [dreamlook.ai](https://docs.dreamlook.ai/welcome-to-dreamlook.ai-docs) that you can use in DiffusionBee.
{% endhint %}

DiffusionBee is a free and open-source Mac application that allows you to generate images on your computer: 

**🔗** [**https://diffusionbee.com**](https://diffusionbee.com/)

The custom models you train on [dreamlook.ai](https://dreamlook.ai/) can easily be used in DiffusionBee, allowing you to create any kind of images of yourself, your pets or anything else you want!

## Step 1: Train your custom model

1. Head to <https://dreamlook.ai/dreambooth> and enable "Expert mode"
2. Select the following parameters:

* "Checkpoint format" must be "**CompVis (AUTOMATIC1111-compatible)"**

<figure><img src="https://3775798052-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FbjzMS9bi5lfz4h6oo4EA%2Fuploads%2FrpylL8ZvOy398Ok7wUE9%2FScreenshot%202023-02-25%20at%2016.22.46.png?alt=media&#x26;token=b35cdec0-a214-40a0-950c-7691880deb82" alt=""><figcaption></figcaption></figure>

You can choose the other options freely such as the number of images, the number of training steps, the base model etc.

## Step 2: Add your custom model to DiffusionBee

After your model is trained, download it to your Mac:

<figure><img src="https://3775798052-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FbjzMS9bi5lfz4h6oo4EA%2Fuploads%2FS4GY2zf1SUo9bstEVmbM%2FScreenshot%202023-07-25%20at%2018.50.54.png?alt=media&#x26;token=c6bf74bc-7478-444e-8971-26a6960bd4b8" alt=""><figcaption></figcaption></figure>

Then add it as a custom model in DiffusionBee:

* Open DiffusionBee settings:

<figure><img src="https://3775798052-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FbjzMS9bi5lfz4h6oo4EA%2Fuploads%2F560NV1SSA4iLLgRLvZRH%2FScreenshot%202023-02-25%20at%2016.27.23.png?alt=media&#x26;token=dbbdbd97-0a84-4e48-bc4c-47d685360f6c" alt=""><figcaption></figcaption></figure>

* In the Settings, under Custom Models, click on "Add New Model" and select the checkpoint you downloaded:

<figure><img src="https://3775798052-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FbjzMS9bi5lfz4h6oo4EA%2Fuploads%2Ft6FFz9cGc5qH14gS4roF%2FScreenshot%202023-02-25%20at%2016.33.12.png?alt=media&#x26;token=bc492914-7dd9-49ac-967b-f9489980cf4e" alt=""><figcaption></figcaption></figure>

* It will now be available as an option in the "Text To Image" tab under "Custom Model":

<figure><img src="https://3775798052-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FbjzMS9bi5lfz4h6oo4EA%2Fuploads%2Fs6mIvxk0AETCPqsYmY2Y%2FScreenshot%202023-02-25%20at%2016.50.23.png?alt=media&#x26;token=4e62acf9-dc76-4a8e-a52c-02027a817040" alt=""><figcaption></figcaption></figure>

## Step 3: Generate images!

You can now generate images using your custom model. This will work with both "Text To Image" and "Image To Image" 🎨🧑‍🎨

<figure><img src="https://3775798052-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FbjzMS9bi5lfz4h6oo4EA%2Fuploads%2FTQepI7AijLQyY0WmXPd3%2FScreenshot%202023-02-25%20at%2016.58.58.png?alt=media&#x26;token=2782fcbe-1fd5-4fbe-ac02-54ab176bf226" alt=""><figcaption></figcaption></figure>

Check out [DiffusionBee's help pages](https://github.com/divamgupta/diffusionbee-stable-diffusion-ui/blob/master/DOCUMENTATION.md#text-to-image) if you need more need guidance about how to use it.