Show HN: We compressed a 31B video+audio diffusion model to 14B, 6 steps, INT8
0 comments
- Points60
- Comments12
–Rank now
#19Peak rank
2Days on list
45Score · 7d
Nov 7, 2026First seen
Rank · 7 days
On Hacker News
- Points
- 60
- Comments
- 12
- Submitted by
- jiant
- Posted
- Nov 7, 2026
- Site
- github.com
Story details from Hacker News ↗ · linked article on github.com.
Trending history
Show HN: We compressed a 31B video+audio diffusion model to 14B, 6 steps, INT8 was first seen on Hacker News · Front page on Nov 7, 2026. Since then it has appeared in 87 checks on 2 different days, across 3 lists (Hacker News · Front page, Hacker News · Show HN, Hacker News · Show HN · this week). Its best position was #19 of 30, reached on Nov 8, 00:09 UTC. It dropped off the list after Nov 8, 14:20 UTC. The same link also trended on GitHub, which raises its cross-platform score.
Rank history
Position on Hacker News · Front page at every check (lower is better).
Last 14 days
Best rank per day (UTC).
20
19
Oct 26today
Metric history
Platform metric as reported by Hacker News.
Where it trended
| List | Best | Days | Checks | Last seen |
|---|---|---|---|---|
| Hacker News · Front page | #19 | 2 | 27 | |
| Hacker News · Show HN | #2 | 2 | 42 | |
| Hacker News · Show HN · this week | #20 | 2 | 18 | |
| GHGitHub · Rising today video-rebirth/hyperflow-h3-flash | same link | |||
From the discussion
A few top-level comments from Hacker News, shortened. Read the full thread on Hacker News.
This is very cool, I wish they would make quality+time comparisons between the various quantisations though
I see references to comfyui in the readme. Is that the easiest way to run it? I've always found it a bit cumbersome to use and wish I had something like a simple CLI tool to use it like llama.cpp. Perhaps that's not possible with a video diffusion model?
Their product page has sample videos: https://www.videorebirth.com/lp/hyperflow-flash
Featured in
Archived daily, weekly and monthly lists that include this entry.
Questions
Is Show HN: We compressed a 31B video+audio diffusion model to 14B, 6 steps, INT8 trending on Hacker News right now?
Not at the moment. It was last on the list on Nov 8, 14:20 UTC, after 2 days of trending.
What is the highest rank Show HN: We compressed a 31B video+audio diffusion model to 14B, 6 steps, INT8 reached?
#19 on Hacker News · Front page, on Nov 8, 00:09 UTC. Trendoday checks this list every 15 minutes.
How long has Show HN: We compressed a 31B video+audio diffusion model to 14B, 6 steps, INT8 been trending?
It was first seen on Nov 7, 2026 and has been on the list on 2 days (87 checks) since.
How much discussion did it get on Hacker News?
60 points and 12 comments; submitted by jiant on Nov 7, 2026.