News for hackers. Stuff that matters.
Re:Flux 3 by zmmmmm on Friday July 24, 2026 @03:05AM (#49032116)
> It jointly learns from images, videos, and audio within a unified architecture, because what it needs to learn is not any one of these elements in isolation.

I'm confused, videos contain images and audio ...?

Re:Flux 3 by ibotty on Friday July 24, 2026 @03:19AM (#49032206)
That's most likely a disagreement on terms. In the media world, video is only the moving images, not audio. This is separate from images, that are meant to be still images.
Re:Flux 3 by PxldLtd on Friday July 24, 2026 @03:22AM (#49032223)
It's more a comment about the feature detection I think; all image, video and audio input contribute to the same weights/activations that can produce image, video and audio output.
Re:Flux 3 by EricBurnett on Friday July 24, 2026 @06:20AM (#49033457)
Video contains images (frames), but not every image would reasonably be found in the frames of a video, or interpreted spatially. In the space of world model synthesis, consider blueprints, relationship diagrams, pages of instructions, sheet music, or a boarding pass.