LaunchVisual AIOctober 30, 2026

Pika launches H3 Flex, open-source omni video model

Read original source →huggingface.co

Pika H3 Flex, post-trained on MiniMax H3, debuts as the #1 open-weight model on DesignArena's text-to-video board and generates faster than realtime in six denoising steps instead of 50. It outputs up to 4K with five editable audio stems and is priced from $0.01/sec.

How this story unfolded

1 day · 1 report · 6 community posts · from Oct 29

  1. Oct 29
  2. Oct 30

More stories today

Open the live feed