HN

Need help?
<- Back
Qwen-Image-3.0: Rich Content, Authentic Details, Deep Knowledge

Qwen-Image-3.0: Rich Content, Authentic Details, Deep Knowledge

ilreb

Comments (122)

  • mynti
    To me it feels so weird that people are trying to push these model for online shopping like "here is how this dress/shirt/pants would look on you". But these models will always make the clothes fit your body and show you in flattering light and so on. How the actual garment fits is still as elusive as before these tools
  • weird-eye-issue
    The meta keywords in the HTML is very interesting. 100+ references to NSFW topics such as hentai, nudes, etc.
  • postalcoder
  • hessammehr
    Very cool but the Arabic text in the title image is obviously and hopelessly broken, which is oddly not the case when actually using the model. Could it be that the hero image was not generated by Qwen Image 3.0?
  • simonw
    > to precisely describe the full 3×3 grid takes a full 3.7k tokensIt's a shame they didn't share that prompt - it would make that demo more convincing.
  • embedding-shape
    Not a single word about when/if they'll actually release the weights for this, or am I missing it somewhere?
  • tarcon
    I am surprised by the rather bad output. It doesn't achieve qwen image 1 quality in composition or anatomical correctness. Tested on chat.qwen.aiI am seeing third legs and glowing eyes. It's a Microsoft Lens level of quality and that one was pulled.
  • timedude
    Zooming in on mobile on that website causes a large white area to obstruct the page. Might wanna look into that.As for the image model, wow...
  • gchokov
    It failed to create a simple overlay on a map - something ChatGPT had no issues with.
  • yoshitha2010
    Estate agents are also doing it; making interiors of houses look very different to how they really are.
  • Mashimo
    > Supports up to 4.5k token input, effortlessly generating complex layouts such as newspapers, storyboards, and exam papers.Impressive.Btw, what is currently the best model to run locally on a 16GB Vram? Is it Z-Image Turbo?
  • sajithdilshan
    I truly wish these models were available when I was in University. As a visual learner it would have been much easier for me to understand certain topics with illustrative diagrams rather than reading a wall of text.
  • pal9000i
    How long until we get rid of the AI "plasticness" in portrait kind of generated images?
  • feverzsj
    The "piss filter" is still everywhere.
  • ninjagoo
    The examples posted on their launch blog page are quite impressive, especially for fine details, multi-panel/multi-page and text rendering.But: not open-source/open-weights, and no indication that weights/source will be released either.
  • bejd
    I wonder if they got permission to generate that (admittedly impressive) Berserk image.
  • ndom91
    Again not released on huggingface immediately?
  • dsrtslnd23
    Seems that this will not be open weights?
  • lifthrasiir
    > In the three examples below, the model accurately renders Japanese, Korean, and Spanish respectively.And yet the Korean text is not accurate... [1][1] E.g. "드레스 컬렉션 dress collection" has vowels ㅔ mixed with ㅐ, "초웜한" should be "초월한 exceeding", "신키한" should be "실키한 silky", "디자언되다" should be "디자인되다 have been designed", "로얼" should be "로열 royal", and so on.
  • Oarch
    I assume Van Gogh didn't paint enough hands to train from!
  • maxloh
    I am curious whether the model requires a font to be installed. Does it also generate the glyphs for the text?
  • dhbradshaw
    The generated latex pdf!
  • Smaily
    why I cant submitte new posts here ? My account since 2016
  • spwa4
    Appears to be closed-weights entirely. No word at all on any weights release.
  • saltysalt
    It will be interesting to compare this to Flux 2.
  • treetalker
    The red-dress woman's vestigial pinkie toes …
  • arslan9063
    THIS IS EXACTLY WHAT I WAS LOOKING FOR
  • xiaoyu2006
    The blog write-up style is so casual haha.
  • jdw64
    Wow, it displays Korean properly without breaking. But there are still a lot of typos. Haha, it's good that Korean displays properly, but there are a lot of incorrect sentences
  • rvz
    Midjourney already knew that image generation was going to zero. Again yet another reason why the model was never a moat in the first place.
  • mahimai
    interesting
  • viridir
    This looks impressive！
  • nttylock
    [flagged]
  • gpjanik
    The real performance is nowhere close to what is presented in the marketing materials, which is pretty annoying. Especially text rendering and accuracy.Try asking it for a plot of Polish GDP growth over the past 20 years. It's slop.