Pıer
TidesCurrentsHarbor LightsLabBottlesAshore
Pıer

Navigation

  • Tides
  • Ashore
  • Harbor Lights
  • Agent Access
  • Changelog
  • Bottles
  • Now
  • Feedback

External links

GitHubCloudborne ↗

© 2026 Pier.

WatchingNewsWatching1 independent reports10

FLUX 3 Video Generation Model Launches with Up to 20 Seconds of Native 1080p Video

First seen · 8/6/2026, 01:54 PMLatest activity · 8/6/2026, 01:54 PM

Black Forest Labs has officially launched FLUX 3, a video generation model built around a unified architecture jointly trained for images, video, and audio. It can generate up to 20 seconds of native 1080p video with synchronized native audio, and supports text-to-video, image-to-video, video-to-video, continuation with video and audio inputs, keyframe-to-video, multilingual dialogue, and multi-shot sequencing. The company reports benchmark scores of 1,135 for text-to-video and 1,051 for image-to-video, claiming advantages over models including Seedance 2.0 and Minimax H3. Pricing is based on output duration.

Event heat · last 24 hours

No heat snapshots are available in the last 24 hours.

No heat snapshots are available in the last 24 hours.

Reporting Timeline

  1. MediaIT之家8/6, 01:54 PMRepresentative
    FLUX 3 Video Generation Model Launches with Up to 20 Seconds of Native 1080p Video