# Stable Diffusion

{% hint style="info" %}
**Big thanks for** [**Stable Diffusion Art**](https://twitter.com/stable_diff_art)**'s and** [**Hugging face Stable Diffusion**](https://huggingface.co/blog/stable_diffusion)**'s article. All the contents come from Stable Diffusion Art's articles. I can't remember these things without writing them down, so I write all of them. And I will correct some of the parts of them and add more personal thinking in the future (14/06/2023).**
{% endhint %}

## Overview

*Stable Diffusion is a text-to-image latent diffusion model* crated by the researchers and engineers from CompVis, Stability AI and LAION. It is trained on 512x512 images from a subset of the LAION-5B database. ***LAION-5B*** is the largets, freely accessible multi-modal dataset that currenctlt exists.

## Credit

{% embed url="<https://stable-diffusion-art.com/controlnet/#What_is_ControlNet>" %}

{% embed url="<https://stable-diffusion-art.com/how-stable-diffusion-work/>" %}

{% embed url="<https://huggingface.co/blog/stable_diffusion>" %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://aisuko.gitbook.io/wiki/ai-techniques/stable-diffusion.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.