Flux 3

I hope the open-weight versions will be SOTA.

> Over the next few weeks and months, we will make the following capabilities available

> Open-weight access to a multimodal backbone, for content creation (video, audio and image) and action prediction. (“FLUX 3 Dev”)

> We will also release more technical details on the underlying approach.

- Showed close to zero examples of people.

- Frivolous use of the term World Model.

- Claims 20 seconds of video, shows only jumpcuts.

Coming soon!

Flux 2 Dev Klein has practically been the best you could use on most commercial hardware so I really hope Flux 3 has a comparable updated open-weights model to it. if not it'd be a great loss to most hobbyists.

It's incredible how negative and dismissive the comments in here are while here I am thinking the model actually looks impressively capable.

But then again I heard the downers have always been the first to leave their dung comments here so let's see...

I wonder if this also creates people with huge heads and short necks like Flux Klein does.

first AI thing coming from Europe that gives high hopes

I have a feeling open-weight models ought to be outperforming proprietary ones by now, but that still hasn’t happened. So far, Nano Banana and GPT-2 Image seem to be the best in class, and Flux still isn’t crossing that quality bar.

I thought the clips were real footage until they were dancing in a flooded room.

> 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 ...?

i don't get why they are investing money on image/video gen. All generations i have see looked blurry, lacking in fine details and missing the artistic touch (lacks meaning? lifeless?)

Open-weight plans are near the bottom (Launch section):

    - Video and audio generation and editing through APIs and private weight access. (“FLUX 3 Video”)
    - Action prediction through selected research and commercial partners, beginning with mimic robotics (“FLUX-mimic and FLUX 3 Action”)
    - Image synthesis and editing through APIs and private weight access. (“FLUX 3 Image”)
    - Open-weight access to a multimodal backbone, for content creation (video, audio and image) and action prediction. (“FLUX 3 Dev”)

Lots of words about multi-modal but then this:

> our mission to develop real-world visual intelligence

Visual is mono-modal, isn't it?

Well, unified multimodal intelligence is the only way we will get to The Terminator, which seems to be the goal now of Silicon Valley and every Nation State with a military budget, so have at.

The fact that people keep developing this technology shows that the true problem is not that machines are likely to become intelligent, but that people have already become machines - unthinking and without any care to the future whatsoever.

Sorry because pointing this is a bit tired by now, but reading already the first two paragraph thete is this unmistakable stench of LLM slop writing. Immediately disengaged.

[dead]

AI slop trained on copyrighted content.

imagine spending nine figures training a model to learn that the sound has to match the impact. my 8-month-old figured that out by dropping a spoon on the floor twice.