Pika post-trains and open-sources Pika H3 Flex video generation model based on MiniMax H3
Original title:@pika_labs 在Minimax的H3上做了后训练,推出了Pika H3 Flex,把视频生成的采样步数从50步压缩到了6步,生成时间大大降低,而且质量甚至还有提升,非常酷的工作,并且直接开源了。
AI summary
Pika Labs post-trained on MiniMax H3 to launch and open-source Pika H3 Flex, cutting sampling steps from 50 to 6, greatly reducing generation time while improving quality.
Key Takeaways
- Pika Labs post-trained on MiniMax H3 to launch and open-source Pika H3 Flex
- cutting sampling steps from 50 to 6
- greatly reducing generation time while improving quality.
Quick Facts
- Published
- Updated
- Source
- X:卡兹克 (@Khazix0918)
- Category
- Model Releases
- AI score
- 68
原文点出采样步数从50步压到6步且开源,本地视频生成玩家可据此评估实际收益。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: Pika post-trains and open-sources Pika H3 Flex video generation model based on MiniMax H3. October 30, 2026. https://new.nat6.net/en/news/eq47lph0rzobf8cr950saiu8r/