# Hugging Face — PRX Part 3 — Training a Text-to-Image Model in 24h!

- Company: Hugging Face (huggingface.co)
- Announced: 2026-03-03T16:50:49+00:00
- Category: research-paper
- Subject: Platform
- Source: https://huggingface.co/blog/Photoroom/prx-part3
- Record: https://forck.live/items/1541-prx-part-3-training-a-text-to-image-model-in-24h

Photoroom describes a 24-hour training speedrun for a text-to-image model using a combination of techniques such as x-prediction in pixel space, perceptual losses, token routing with TREAD, and representation alignment with REPA, and open-sources the code.

## Evidence

Verbatim from https://huggingface.co/blog/Photoroom/prx-part3:

> we’re doing a 24-hour speedrun: 32 H200 ~ $1500 total compute budget

---

Record: https://forck.live/items/1541-prx-part-3-training-a-text-to-image-model-in-24h
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md