# Kohya in the Cloud

Kohya is the go-to for model creators, providing a dedicated UI focused on allowing you to quickly train and fine-tune your own models, LoRAs and Textual Inversions.

**Why use Kohya?**

* You’re a badass model creator who can train a base model (SD1.5 & SDXL) using Dreambooth.
* You want to train LoRAs (SD1.5 & SDXL). The most popular use case is to create SDXL LoRAs for character-specific or style-focused enhancements that the base SDXL model does not cover.
* You want to create Textual Inversions / Embeddings

<a href="https://www.thinkdiffusion.com/select-machine/featured/kohya/current/ultra" class="button primary">Run Kohya in the Cloud</a>

## Some awesome Kohya tutorials to get started:

{% embed url="<https://www.youtube.com/watch?v=pQ0RzNNlKQk>" %}

{% embed url="<https://www.youtube.com/watch?v=j-So4VYTL98>" %}


---

# 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://docs.thinkdiffusion.com/kohya-in-the-cloud.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.