HN

Need help?
<- Back
Flux 3

Flux 3

ThouYS

Comments (91)

  • user43928
    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.
  • thisisauserid
    - Showed close to zero examples of people.- Frivolous use of the term World Model.- Claims 20 seconds of video, shows only jumpcuts.Coming soon!
  • jdthedisciple
    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...
  • tormeh
    These people are hiring in... Freiburg im Breisgau? Wonder how hiring is working out for them there.
  • pwillia7
    Awesome -- glad they're going to release the open weight version! I've been waiting for an excuse to re jump into AI OS image gen!
  • make_it_sure
    first AI thing coming from Europe that gives high hopes
  • OldMatey
    I am very excited for this. 2.3 was excellent and I've seen clips from people who got early access along with reading their reflections on it and I think this will be the new SOTA for home use.
  • Tenoke
    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.
  • Gecko4072
    I thought the clips were real footage until they were dancing in a flooded room.
  • anon
    undefined
  • yangcheng
    I hope flux will include a 3D generation model. right now the open-weights version of 3D is failing behind closed source by a big margin. Hopefully the improved spatial ability helps with robotics too
  • NSUserDefaults
    > a model must learn a representation of the world: […] and how events soundI honestly hope they put an unrealistic amount of wilhelm scream into the learning process, just for fun.
  • zmmmmm
    > 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 ...?
  • abdusco
    I wonder if this also creates people with huge heads and short necks like Flux Klein does.
  • rekpero
    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.
  • teiferer
    Lots of words about multi-modal but then this:> our mission to develop real-world visual intelligenceVisual is mono-modal, isn't it?
  • mattmanser
    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”)
  • saejox
    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?)
  • SubiculumCode
    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.
  • frotaur
    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.
  • anon
    undefined
  • vouaobrasil
    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.
  • vladsiu
    [dead]
  • doitright99
    AI slop trained on copyrighted content.
  • luciana1u
    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.