# Introducing Post Illustrations: Enhance Your Discourse Content with AI-Generated Thumbnails

**URL:** <https://meta.discourse.org/t/introducing-post-illustrations-enhance-your-discourse-content-with-ai-generated-thumbnails/290870>\
**Category:** Announcements\
**Tags:** ai, ai-helper\
**Created:** [January 8, 2024, 2:23pm UTC](https://meta.discourse.org/t/introducing-post-illustrations-enhance-your-discourse-content-with-ai-generated-thumbnails/290870 "2024-01-08T14:23:56Z")\
**Posts on this page:** 1\
**Showing post:** 23

<div class="post-metadata">

**Author:** ![dsims](https://sea3.discourse-cdn.com/meta/user_avatar/meta.discourse.org/dsims/32/485916_2.png) [@dsims](https://meta.discourse.org/u/dsims)\
**Post date:** [June 14, 2024, 1:37pm UTC](https://meta.discourse.org/t/introducing-post-illustrations-enhance-your-discourse-content-with-ai-generated-thumbnails/290870/23 "2024-06-14T13:37:40Z")

</div>

Could there be a way to generate images with _only_ a StableDiffusion key? (I’m not interested in the other helper features at the moment) I see currently you need a LLM configured to generate a more descriptive StableDiffusion prompt. So maybe a “fake” LLM that simply passes the post content as the prompt?

---

_[View the full topic](https://meta.discourse.org/t/introducing-post-illustrations-enhance-your-discourse-content-with-ai-generated-thumbnails/290870)._