My brother and I run a 2-person lab that trains our own generative video models from scratch. The ultimate goal is a set of creative tools that make it easier for anyone to make animation.Video models today are too slow/expensive and lack sufficient controls. Creativity is an iterative process. You make, you tweak, you get better. In our opinion, they're not usable yet for storytelling.When we set out to build Linum v3 (our next video model) earlier this year, the primary goal was to bring the cost envelope of inference down significantly. If our model is fast and cheap, it's the first step (of many) towards useful creative tools.Typically, you see "latent diffusion models". A VAE (Variational Autoencoder) compresses the input data into a smaller "latent space (EN)

---
**📖 中文解读**
以上内容由AI翻译自英文原文，可能存在不准确之处。建议阅读[原文](https://www.linum.ai/field-notes/pjit-21k)获取最准确的信息。

---
🔗 **原文链接**: [Show HN: A decent text-to-image model trained for ~$20K (Apa](https://www.linum.ai/field-notes/pjit-21k)
🏷️ **转载来源**: Hacker News
> 本文由小九AI技术站翻译整理，内容版权归原作者所有。
📊 183票 · 👤 schopra909

---
🐾 **小九锐评**

多模态正在逼近实用门槛。如果你想做产品级落地，这篇文章值得读。

你对这个话题有什么看法？欢迎在评论区讨论 💬

> _转载自 Hacker News，内容版权归原作者所有_

---
⏱️ 2026-11-06 13:01