‹ BackHN Continuity

Thread

FLUX 3 Image

437 points · 96 comments · minimaxir

  1. vunderba · · focus · HN ↗
    One of the things they seem to be emphasizing here is the UX around being able to place specific elements where you want them in an image. If the positions of the components in the overall composition are very important, this seems to make that a lot easier and kind of reminds me of InvokeAI.

    Ideogram V4, an open-weight model released back in June can also do this [1], but you have to use a relatively cumbersome JSON structure to describe all the different bounding boxes. So it’s definitely a bit of a hassle.

    I'll probably be waiting until it goes open-weight (hopefully soon) like they did with Flux.2 / Klein.

    [1] - <a href="https:&#x2F;&#x2F;docs.ideogram.ai&#x2F;using-ideogram&#x2F;getting-started&#x2F;prompting-guide&#x2F;4.-json-prompting-ideogram-4.0" rel="nofollow">https:&#x2F;&#x2F;docs.ideogram.ai&#x2F;using-ideogram&#x2F;getting-started&#x2F;prom...

    1. kranke155 · · focus · HN ↗
      You just get an LLM to do the bounding box stuff or use the ComfyUI node that provides a GUI for bounding box generation
      1. CuriouslyC · · focus · HN ↗
        I always hated Comfy&#x27;s node based UI, but agents make it tolerable. Now I just have them set up a workflow and I go in and tweak it manually if the results aren&#x27;t where I want them. I even have agents cherry doing multiple runs and cherry picking the best outputs, models have gotten good enough that it&#x27;s a real time saver, assuming you have references they can and a rubric to check against.
        1. swiftcoder · · focus · HN ↗
          &gt; I always hated Comfy&#x27;s node based UI

          It&#x27;s one of the most uniquely hostile user experiences I&#x27;ve ever had the (dis)pleasure of working with

          1. orbital-decay · · focus · HN ↗
            I remember precisely how ComfyUI started, and the motivation was something along the lines of &quot;look at the cool guys working in Houdini and Resolve, they must know something&quot; (I wish I was kidding). Of course nobody thought that DAGs are just poorly suited for the task, even when plugin authors started trying to slap loops on top of them shortly after that.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.