Video: what I’ve logged
Video comes up in 2 posts of my AI log, from October 2026 to November 2026, and each item below links to the primary source. The sources come from Google, NVIDIA and Luma, filed under frontier, open weights and image, video, world.
Items that mention Video
- Google 5 Nov 2026
Introducing Gemini Omni 1.2 Flash
Video generation and editing now reaches 15 seconds per clip, up from 10, at 30% lower cost than Omni 1.1, or $0.07 per second at 720p.
- NVIDIA 5 Nov 2026
New NVIDIA Cosmos 3 Open Models for Interactive World Simulation
Four open-weight checkpoints post-trained from Cosmos 3 Nano, covering multi-view driving data, streaming camera and LiDAR, simulator-to-video and two-arm robot prediction.
- Luma 22 Oct 2026
Kling 4.0 in Luma: Fast Action and Big Camera Moves
Kling 4.0 is now selectable on Luma boards for tracking shots, orbits and push-ins, in text-to-video and image-to-video, across four aspect ratios.