pika-labs/pika-h3-flex
Pika H3 Flex: video and audio generation inference
- Stars2008
- LanguagePython
- LicenseOther
Pika H3 Flex: video and audio generation inference
Pika H3 Flex: video and audio generation inference
Pika H3 Flex is a post-trained H3 model, designed to give professional creators the flexibility and speed to explore with precision. Optimized for greater control, it generates video with synchronized audio in six sampling steps and supports up to 12 reference inputs, with shot direction through references and prompts.
Pika’s hosted API extends this workflow with 1080p, 2K and 4K video generation, audio stems and prompt enhancement. Local open-weight inference supports native 480p / 768p video with mixed stereo audio.
Description and README excerpt from Pika-Labs/Pika-H3-Flex on GitHub ↗.
pika-labs/pika-h3-flex was first seen on GitHub · Rising today on Nov 6, 2026. Since then it has appeared in 197 checks on 3 different days, across 2 lists (GitHub · Rising today, GitHub · Rising this week). Its best position was #1 of 30, reached on Nov 6, 18:30 UTC. It dropped off the list after Nov 8, 06:15 UTC.
Position on GitHub · Rising today at every check (lower is better).
Best rank per day (UTC).
Platform metric as reported by GitHub.
| List | Best | Days | Checks | Last seen |
|---|---|---|---|---|
| GitHub · Rising today | #1 | 3 | 125 | |
| GitHub · Rising this week | #1 | 2 | 72 |
Archived daily, weekly and monthly lists that include this entry.
Not at the moment. It was last on the list on Nov 8, 06:15 UTC, after 3 days of trending.
#1 on GitHub · Rising today, on Nov 6, 18:30 UTC. Trendoday checks this list every 60 minutes.
It was first seen on Nov 6, 2026 and has been on the list on 3 days (197 checks) since.
Mostly Python; it is licensed under Other. It has 2008 stars and 39 forks.