Physix Frontier badgePhysix Frontier
PublishChinese | EN

Physix Frontier · News Briefing Card (Hacker News · Oct 16, 2026)

Kling 4.0 launches with text-to-video and image-to-video

KEY FACTS

  • Kling 4.0 supports two input modes: text-to-video and image-to-video.
  • Users can specify motion, camera path, and ending, and adjust duration and format.
  • The page offers Flash and Pro creation options, with a credit estimate shown before generation.
  • The full model is claimed to support up to 10 keyframes and 15 multimodal references.
  • The company says access, pricing, and API details for the full model will be updated separately.

KEY DATA

10Keyframe limit
15Multimodal reference limit

PHYSIX OBSERVATION

By pushing up the keyframe and reference-image counts, Kling 4.0 is clearly moving toward a controllable, film-grade workflow rather than just flashy short clips. For production teams, the real barrier has shifted from generation quality to how to plug AI into existing storyboard and review pipelines; whoever solves that first gets the orders first.

Source: Hacker News report