---
metadata:
  - name: generator
    content: Diplodoc Platform v5.63.0
alternate:
  - https://yandex.com/support/shedevrum/en/picture/create.md
  - href: https://yandex.com/support/shedevrum/en/picture/create.md
    type: text/markdown
    title: Markdown version
  - href: https://yandex.com/support/shedevrum/en/llms.txt?revision=r21455420
    rel: describedby
---
> **Documentation Index:** Fetch the complete configuration index at https://yandex.com/support/shedevrum/en/llms.txt?revision=r21455420

<!-- source: en/_includes/18-warning.md -->
 {% note warning %}
        
  Shedevrum is intended for users aged 18 or older. 
  
  Minors can only use the service in [Kids mode](https://yandex.com/support/shedevrum/en/children.md).
        
  {% endnote %}
<!-- endsource: en/_includes/18-warning.md -->

# How to generate

Shedevrum uses a neural network to help you generate an image or apply [filtrums](https://yandex.com/support/shedevrum/en/picture/filtrum.md) to your photo.

To create an image using the neural network:

1. Tap ![](../_image/create.svg) at the bottom and select **Image**.

1. Open the list of models and choose one:

   - Alice AI ART model **v.1.0** is more accurate at following your prompts and better at bringing your vision to life.
   - YandexART models:
       - **v.2.7** creates sharper and more detailed images compared to previous versions.       
       - **v.2.5** generates images with text in Latin script and automatically selects the optimal style for your prompt.       


1. Describe the image you want to get:

     - Describe the image in your own words. The more detailed your description is, the more relevant the generated image will be. For example, instead of "a lamb in the sky", enter "a fluffy lamb cloud flying in the sky, cute, gentle, colorful starry sky, 4k quality". You can describe the image in any language.

     - To generate a description, tap ![](../_image/for-me.svg).

1. Tap **Create**. The neural network will start generating the image. It usually takes under a minute.

    {% note info %}
    
    Images are generated in low quality, but the quality and sharpness are improved when you publish the image.
    
    {% endnote %}

    To stop the generation:

      - iOS: Tap **Cancel**.
      - Android: In the top-right corner, tap ![](../_image/close.svg) → **Stop**.

1. Change the generated image:

     - To generate another image from the same description, tap ![](../_image/update.svg) at the bottom.
	
	- To change the description, tap your prompt and edit it. Tap **Create**.

     - To delete the image, tap ![](../_image/delete.svg) in the menu below.

1. Prepare your image for posting:

     - Add hashtags — tap ![](../_image/hashtag.svg) in the menu under the image.
     

1. Select one of the generated images and tap **Done** at the bottom. The image appears in your profile and other users' feeds.
    
     After the image is published, you can share or download it.

<!-- source: en/_includes/button-content.md -->
<a href="en/content">
  <span class="button">Go to table of contents</span>
</a>


<!-- endsource: en/_includes/button-content.md -->

<!-- source: en/_includes/feedback-button.md -->
<a href="en/feedback">
  <span class="button">Contact support</span>
</a>


<!-- endsource: en/_includes/feedback-button.md -->
