Google Flow has introduced video editing features.
One of the cool ones: object insertion — you just choose where you want to place the object and describe it. Flow will generate the object and seamlessly integrate it into your clip.

WOW! First time in the Longshot: Full 1 Minute AI Movies From One Prompt, with consistent characters. Forget those 5-second clips, it’s time for real storytelling.

With Longshot, you can generate a full 1-minute cinematic video complete with music, dialogue, and consistent characters — all from a single prompt. Type your story, upload your hero, and watch it come alive like a movie.

Try it now: https://vortex.channel/longshot

They’re adding video upscaling to Grok.
But it’s only for Grok Imagine Videos, meaning videos generated within Grok itself.
And apparently, it’s only available in the desktop version.
It upscales to HD in about 10 seconds.

Imagine typing a simple idea — and watching it come alive as a full cinematic scene with acting, lighting, motion, and emotion. No crew. No animation tools. Just pure AI filmmaking. Welcome to Vidu Q2, the next-generation AI model that transforms imagination into real moving cinema. In this episode, we explore what makes Vidu Q2 revolutionary — from its Reference-to-Video (reference to the video) system that blends up to 7 reference images into one coherent video, to its upgraded Image-to-Video engine that brings unmatched motion realism, stable faces, and emotional depth. Vidu Q2 doesn’t just generate clips — it performs them. With real camera work, micro-expressions, and fluid storytelling, this model is redefining what “AI video generation” means.
https://www.youtube.com/watch?v=hEbtpJIYcLo

The little Unitree G1, weighing 35 kg, is pulling a car that weighs 1,400 kg.
Sure, it’s on a parking lot and not in a forest, so it’s not that hard — but still, pretty cool!

MiniMax Music 2.0
Tracks are FIVE minutes long Precise control over musical arrangement and instruments is announced A cappella and duets (interesting) And of course, it’s all “studio quality and stuff” Available on the website: https://www.minimax.io/audio/music And on Fal: https://fal.ai/models/fal-ai/minimax-music/v2
But of course, they’re still far from Suno.

OmniX: From Unified Panoramic Generation and Perception to Graphics-Ready 3D Scenes
Here’s an open-source project from Kling.
They don’t just generate panoramas — along the way, they also extract various properties: depth maps, normals, albedo, roughness, and metallic. But the most interesting part is that they claim to be able to convert panoramas into 3D — specifically into regular meshes that can then be loaded into Blender. Although this feature is marked as completed on GitHub, there’s a note in small print saying it’s still rough around the edges, sort of a beta version.
Project: https://yukun-huang.github.io/OmniX/