---
title: "Discussion on \"Why Is the RAP Poster Dataset Built on Markup, Not Pixels?\" | Hashnode"
description: "Discussion on \"Why Is the RAP Poster Dataset Built on Markup, Not Pixels?\". Originally published at vinpatel.com\nWhy would a poster-generation dataset ship markup instead of images? Because the model never has to draw. It writes a declarative description of the layout, and a"
url: "https://hashnode.com/posts/why-is-the-rap-poster-dataset-built-on-markup-not-pixels/6ad5c66916ce5809ca96b138"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [Why Is the RAP Poster Dataset Built on Markup, Not Pixels?](https://vinpatel.hashnode.dev/why-is-the-rap-poster-dataset-built-on-markup-not-pixels?utm_source=hashnode&utm_medium=feed)

Originally published at vinpatel.com Why would a poster-generation dataset ship markup instead of images? Because the model never has to draw. It writes a declarative description of the layout, and a

Oct 19 · 3 min read · vinpatel.hashnode.dev  
Read the article

-   [#artificial-intelligence](https://hashnode.com/tag/artificial-intelligence)
-   [#llm](https://hashnode.com/tag/llm)
-   [#models](https://hashnode.com/tag/models)
-   [#developer-tools](https://hashnode.com/tag/developer-tools)

## Written by

[Vin Patel](https://hashnode.com/@vin-patel)

@vin-patel · New York City, USA

  
[View profile](https://hashnode.com/@vin-patel)

I build AI tools, write books, and ship open-source software.

## Responses

Markdown supported · ⌘↵ to post

No responses yet.