Pika open-sources H3 Flex video generation model
What happened
On October 30, AI HOT reported that Pika Labs post-trained on MiniMax H3 to release and open-source the video generation model Pika H3 Flex. The release focuses on generation efficiency and quality: sampling steps drop from 50 to 6, and the report says generation time falls sharply while quality improves. The model is out and open-sourced; the report gives no specific generation times, quality benchmark results or open-source license details.
Written by AI from the coverage · updated 3 hours ago
Coverage
Follow the reports to see the story from different sides.
- AI HOT · ModelsPika Labs 基于 MiniMax H3 后训练并开源 Pika H3 Flex 视频生成模型
Pika Labs 基于 MiniMax H3 进行后训练，推出并开源视频生成模型 Pika H3 Flex。其采样步数从50步压缩到6步，生成时间大幅降低，质量有所提升。
Heat over time
Heat now 9·Comparable peak 10（Oct 30 05:00）·Comparable change over 24 hours –
The trend only compares accounts observed without gaps, so its range may be smaller than the current heat. Hover or tap the chart for each hour; the left and right arrow keys step through it.