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

DevFeed: [PRX Part 3 -- Training a Text-to-Image Model in 24h!](<https://devfeed.tech/articles/prx-part-3-training-a-text-to-image-model-in-24h-7037.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/Photoroom/prx-part3>)

Author: David Bertoin; Roman Frigg; Jon Almazán

Published: 2026-03-03T16:50:49Z

Content type: article

Language: en

Sources: [Hugging Face - Blog](<https://devfeed.tech/sources/hugging-face-blog.md>)

Topics: [text-to-image](<https://devfeed.tech/topics/text-to-image.md>), [GPU](<https://devfeed.tech/topics/gpu.md>), [Code](<https://devfeed.tech/topics/code.md>), [Hardware](<https://devfeed.tech/topics/hardware.md>)

Tags: [code](<https://devfeed.tech/tags/code.md>), [compute](<https://devfeed.tech/tags/compute.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [cost](<https://devfeed.tech/tags/cost.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [experiment](<https://devfeed.tech/tags/experiment.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [model](<https://devfeed.tech/tags/model.md>), [open](<https://devfeed.tech/tags/open.md>), [performance](<https://devfeed.tech/tags/performance.md>), [text-to-image](<https://devfeed.tech/tags/text-to-image.md>), [training](<https://devfeed.tech/tags/training.md>)

## AI overview

The article describes a 24-hour speedrun for training a text-to-image diffusion model by combining architectural and training techniques from earlier posts. It targets 512px training followed by 1024px fine-tuning on 32 H200 GPUs within an approximately $1,500 compute budget, and says the training code and experimental framework will be open-sourced.

## Source excerpt

Welcome back 👋 In the last two posts (Part 1 and Part 2), we explored a wide range of architectural and training tricks for diffusion models. We tried to evaluate each idea in isolation, measuring throughput, convergence speed, and final image quality, and tried to understand what actually moves the needle. In this post, we want to answer a much more practical question: What happens when we combine all the tricks that worked?