Show HN: A decent text-to-image model trained for ~$20K (Apache 2.0 Weights)
0 comments
- Points281
- Comments29
–Rank now
#11Peak rank
4Days on list
172Score · 7d
Nov 5, 2026First seen
Rank · 7 days
On Hacker News
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…
- Points
- 281
- Comments
- 29
- Submitted by
- schopra909
- Posted
- Nov 4, 2026
- Site
- linum.ai
Story details from Hacker News ↗ · linked article on linum.ai.
Trending history
Show HN: A decent text-to-image model trained for ~$20K (Apache 2.0 Weights) was first seen on Hacker News · Front page on Nov 5, 2026. Since then it has appeared in 159 checks on 4 different days, across 2 lists (Hacker News · Front page, Hacker News · Show HN · this week). Its best position was #11 of 30, reached on Nov 6, 15:22 UTC. It dropped off the list after Nov 8, 14:50 UTC.
Rank history
Position on Hacker News · Front page at every check (lower is better).
Last 14 days
Best rank per day (UTC).
17
11
Oct 26today
Metric history
Platform metric as reported by Hacker News.
Where it trended
| List | Best | Days | Checks | Last seen |
|---|---|---|---|---|
| Hacker News · Front page | #11 | 2 | 90 | |
| Hacker News · Show HN · this week | #7 | 4 | 69 |
From the discussion
A few top-level comments from Hacker News, shortened. Read the full thread on Hacker News.
Amazing. I think this is an understudied areas. The big labs if anything are disincentivized to make efficient models as currently access to compute is one of their moats. That's not the same for Chinese labs, which is why you see groundbreaking efficiency work mostly coming from China. Really happy to see a small…
It looks really good! Except almost every hand is wrong. I'm guessing that's a training data thing? Can you tell us more about the 660M training images and prompts? Where did they come from and what do they cover? (I've seen the README say text was excluded.)
Well done. $20k? That's insane. I remember tinyllama back in the day (2023) was trained on $40k and could barely form coherent sentences. Are pictures easier than English, or did the methods advance so much? Edit: I guess I should have said, are pictures plus English easier than English! >The text representation…
Featured in
Archived daily, weekly and monthly lists that include this entry.
Hacker News 2 days, best #11
Questions
Is Show HN: A decent text-to-image model trained for ~$20K (Apache 2.0 Weights) trending on Hacker News right now?
Not at the moment. It was last on the list on Nov 8, 14:50 UTC, after 4 days of trending.
What is the highest rank Show HN: A decent text-to-image model trained for ~$20K (Apache 2.0 Weights) reached?
#11 on Hacker News · Front page, on Nov 6, 15:22 UTC. Trendoday checks this list every 15 minutes.
How long has Show HN: A decent text-to-image model trained for ~$20K (Apache 2.0 Weights) been trending?
It was first seen on Nov 5, 2026 and has been on the list on 4 days (159 checks) since.
How much discussion did it get on Hacker News?
281 points and 29 comments; submitted by schopra909 on Nov 4, 2026.