# AI-beeldonderschriftfunctie in Discourse AI-plugin

**URL:** https://meta.discourse.org/t/ai-image-captioning-feature-in-discourse-ai-plugin/296087
**Category:** Announcements
**Tags:** ai, ai-helper
**Created:** [20 februari 2024 om 17:53 UTC](https://meta.discourse.org/t/ai-image-captioning-feature-in-discourse-ai-plugin/296087 "2024-02-20T17:53:28Z")
**Posts on this page:** 1
**Showing post:** 17

<div class="post-metadata">

### Author: ![Falco](https://sea3.discourse-cdn.com/meta/user_avatar/meta.discourse.org/falco/32/179432_2.png) [@Falco](https://meta.discourse.org/u/Falco)
#### Post date: [15 maart 2024 om 15:46 UTC](https://meta.discourse.org/t/ai-image-captioning-feature-in-discourse-ai-plugin/296087/17 "2024-03-15T15:46:57Z")

</div>

We are running the full model, but the smallest version of it with Mistral 7B. It’s taking 21GB VRAM in our single A100 servers, and it’s ran via `ghcr.io/xfalcox/llava:latest` container image.

Sadly the ecosystem for multi-modal models ain’t as mature as the text2text ones, so we can’t yet leverage inference servers like vLLM or TGI and are left with those one-off microservices. This may change this year, multimodal is on vLLM roadmap, but until then we can at least test the waters with those services.

---

_[View the full topic](https://meta.discourse.org/t/ai-image-captioning-feature-in-discourse-ai-plugin/296087)._