Sora Adds "Extensions" for Longer Scene Continuity
OpenAI introduced Extensions, and early creator tests focus on whether longer clips preserve narrative consistency.
Desk coverage
Model Wire
11 stories in this desk · last updated Feb 24, 2026.
Veo 3.1 Expands Vertical Video and Mobile-Oriented Output
Google’s updates to Veo 3.1 push mobile-first output and stronger image-to-video consistency for social formats.
Luma Positions Ray3 as a Reasoning Model for HDR Video Workflows
Luma frames Ray3 as a reasoning model for production-grade cinematic output and agency workflows.
Product Hunt Is Turning Into a Fast Signal Board for AI Video Utility
AI and Video topic boards reveal where tool demand is clustering around practical production functions.
ByteDance Launches Seedance 2.0, Pushing Longer Clips and Native Audio
ByteDance introduced Seedance 2.0 with claims around longer generation, multimodal control, and synchronized audio-video output.
Kling 3.0 Announced With Native 4K at 60fps, Multi-Shot Generation, and Synchronized Audio
Kuaishou announced Kling 3.0 on January 31, featuring native 4K 60fps output, up to six camera cuts per generation with visual consistency, and synchronized audio-visual output in a single pass.
Luma Ships Ray 3.14 With Native 1080p, 4x Faster Generation, and 3x Lower Cost
Luma AI released Ray 3.14 on January 26, delivering native 1080p output without post-upscaling, alongside major speed and cost improvements.
Google Officially Releases Veo 3.1 With Native 4K, Vertical Video, and Scene Extension
Google DeepMind released Veo 3.1 on January 13, introducing professional 4K upscaling, native 9:16 vertical output, and Scene Extension technology for narratives exceeding 60 seconds.
ByteDance Launches Seedance 1.5 Pro With Joint Audio-Visual Generation
ByteDance officially released Seedance 1.5 Pro on December 16, introducing joint audio-visual generation that creates video and audio simultaneously from text and image prompts.
Runway Launches GWM-1, Its First General World Model Family
Runway released GWM-1, an autoregressive model family built on Gen-4.5, spanning explorable environments, interactive avatars, and robotic simulation.
Kling Kicks Off Omni Launch Week With O1, a Unified Multimodal Video Model
Kuaishou unveiled Kling O1, positioning it as the industry's first unified multimodal creation tool that consolidates text, video, image, and subject inputs into a single generation and editing engine.