Live data from Hacker News

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

qwen.ai

181–190 of 241 posts

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

#181

Not a single word about when/if they'll actually release the weights for this, or am I missing it somewhere?

After Z-Image and the original Qwen-Image - I think they've pivoted completely to closed source. From the images I've seen, Qwen-Image 3.0 is just a subpar equivalent to other proprietary models like gpt-image-2 and nb-pro.

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

#182
once a.i images took over - a lot of things that were based on images died.

going to a fancy restaurant coz of 'you can take good pics' - dead - a.i can recreate that cheaper.

which means for a certain demographic - dating apps are dead too - since those were largely based on swiping photos.

the premium of in-person / small intimate events has gone up. likewise meeting in person, or doing things with a person live.

this also means imperfection has gone up in value (imperfection is a human quality).

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

#183
post #33

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

I have a similar use case at work for previewing construction material and such in our catalogue applied to user uploaded images. Results are mixed, expensive, but it really feels you're few months off the next improvement to really nail it. It's already good enough. Wonder what Qwen image will provide over nano banana.

Well from the images I've seen they seem to be pushing text-heavy "infograph" capabilities pretty hard. Outside of that, I have serious doubts that it'll be better than other proprietary models like NB Pro and gpt-image-2.

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

#184
post #56

I am curious whether the model requires a font to be installed. Does it also generate the glyphs for the text?

It's a proprietary model as a service - it doesn't require anything outside of a browser. But even when they released open-weight (the original Qwen-Image) it's a diffusion model and can't use custom font files.

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

#185
post #57

Earlier quoted context omitted.

That's hilarious. These keywords are applied globally, even on pages like https://qwen.ai/usagepolicy , where they very kindly ask you not to use their products for sexual content. Run this in console to see all the tags: document.querySelector('meta[name="keywords"]').content

WTF lol who made qwen stefani's dress spiderman into the spider verse did qwen meet Peter qwen stacey porn do blake shelton and qwen stafani have children together

I've been thinking about this too much because it's so ridiculous and funny that I had to at least try wrapping my head around it. My best guess is this:

If you look at past snapshots at archive.org, you notice that the meta keywords are growing like an append-only list, which means it's probably part of some messed up seo pipeline. The other clue is that it's stuffing the meta keywords which apparently only Yandex uses as a search signal[0].

The list has 3882 entries. A lot of them are clustered and look like auto-complete results. But a bunch of them look like hyper-specific, misspelled search results (e.g. "145 gwen rd cheshire ct"). Google's webmaster tools doesn't provide distinct queries like that, but yandex's does[1].

My best guess of what's happening is that Qwen is monitoring it's search queries in Yandex, dumping that list into a serp service that scrapes yandex's autocomplete suggestions, and then taking that list and dumping it into their meta keywords.

It explains the urls in the list (ppls using search engines like address bars), the seeming fixation around certain topics (which usually starts with a misspelling), and the random one-off queries.

0: https://yandex.com/support/webmaster/en/controlling-robot/me...

1: https://yandex.com/support/webmaster/en/service/popular-quer...

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

#186
post #182

once a.i images took over - a lot of things that were based on images died. going to a fancy restaurant coz of 'you can take good pics' - dead - a.i can recreate that cheaper. which means for a certain demographic - dating apps are dead too - since those were largely based on swiping photos. the premium of in-person / small intimate events has gone up. likewise meeting in person, or doing things with a person live. t…

the era of wabi-sabi is among us.

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

#187
post #33

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

The short-term goal of a tool like this is to sell products. The more ambitious long-term goal is to shift cultural norms, blurring the lines between advertising and reality until the question you're asking is no longer consciously asked. At least, not by average people, and not at the point of purchase. I find it easy to envision a world, maybe 50 years from now, in which the very concept of "truth in advertising" i…

> I find it easy to envision a world, maybe 50 years from now, in which the very concept of "truth in advertising" is viewed as a lost, idyllic fantasy. Something people are nostalgic for, but feel powerless to regain.

It's infuriating the amount of effort people will expend to claim that what was achieved in the past is literally impossible to do now. It's pervasive, especially from allegedly-smart people like software engineers.

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

#189

How long until we get rid of the AI "plasticness" in portrait kind of generated images?

The right models and LORAs can get rid of it right now. People apparently really like everyone to look like over exposed over filtered mannequins, so the big companies target that look.

I think it's unintentional. People usually dislike any recognizable "AI look", but they do like other aspects which might have an unrealistic AI look as a side effect.

For example, Google's Imagen 3 usually looked a lot less fake than the newer Imagen 4, but the latter still scored higher on most benchmarks because it made fewer mistakes and had better prompt following capabilities.

A similar thing happened with Dalle-E 2 and Dell-E 3: The new model was better but also more fake looking.

Post reply on HN