Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

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

qwen.ai

Post reply on HN
Print view View original

201–210 of 241 posts

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

#201

Post by phainopepla2 »

stavros wrote: post #175
smith7018 wrote: post #139

Earlier quoted context omitted.

Many product/model shots actually use clips to make the clothing look like it's perfectly fitted to the body. [1] This image is actually over 15 years old at this point. I think there should be laws that prevent this because it veers into false advertising though others believe it's alright because you can theoretically tailor the clothes to fit like this. Regardless, I'd rather see real clothing on a real person whe…

That image isn't from a clothes catalog, they'd generally use the unaltered garment there.

Nope. I used to assist a photographer who did shoots for catalogs, and clips were used quite a bit. The same model has to wear dozens of pieces of clothing throughout the shoot, and not everything is going to fit their body well, but the clients obviously want everything to look well fitted.

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

#202

Post by ssalka »

weird-eye-issue wrote: post #9

The meta keywords in the HTML is very interesting. 100+ references to NSFW topics such as hentai, nudes, etc.

I think the Qwen team is probably aware that the NSFW community is very quick to adopt any new image gen model (see: Civitai). So, it seems like a good SEO approach to try and surface their model in search results that said community is likely already checking.

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

#203

Post by throwup238 »

mikepurvis wrote: post #146
k2enemy wrote: post #82

Earlier quoted context omitted.

I've noticed something similar in Facebook marketplace ads for used furniture. Most of the images are AI generated to look like a Pottery Barn catalog, then the last image will be the actual item, full of scratches and other damage, sitting in a messy garage.

I've started to see this on Etsy and Wayfair too, where there will be a listing that is clearly just MDF flatpack being resold from China, but the AI-generated images wildly exaggerate the proportions of it. Here's a recent example: https://www.etsy.com/ca/listing/4509158065/corner-wall-shelf... Ironically, ChatGPT is decently good at ferreting these out. Like I sent it a screenshot of that listing and it not only he…

The merchant is even called “VibesPlante”

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

#204

Post by dleeftink »

palmotea wrote: post #187
teraflop wrote: post #152

Earlier quoted context omitted.

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 softw…

Software has a dependency contract that is quite unique. We can't imagine the shelflife beyond the Bazaar or Cathedral. They seem ever lasting.

The myth of impossibility remains, because we can't imagine what it means to forever occupy those places, even when others rise past them.

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

#205

Post by stavros »

phainopepla2 wrote: post #201
stavros wrote: post #175

Earlier quoted context omitted.

That image isn't from a clothes catalog, they'd generally use the unaltered garment there.

Nope. I used to assist a photographer who did shoots for catalogs, and clips were used quite a bit. The same model has to wear dozens of pieces of clothing throughout the shoot, and not everything is going to fit their body well, but the clients obviously want everything to look well fitted.

Ah, I stand corrected, thanks.

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

#206

Post by Izmaki »

woadwarrior01 wrote: post #119
Izmaki wrote: post #71

Earlier quoted context omitted.

> We implemented safety measures across the full model development lifecycle. Any suggestions for the best open, non-opinionated model?

It is a reasonably non-opinionated model. My usual test is to ask these models to generate comic book and cartoon characters that hosted image generation models refuse to generate. I think that text is just CYA legalese.

What's your favourite (online or offline) model for image generation?

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

#207

Post by HawtAds »

zzleeper wrote: post #162

Random question, but has there been any improvement in OCR/document understanding in these newer models? Last time I checked (1mo ago) SOTA was still sadly Gemini, unless you wanted to pay $$$ for e.g. Sol

Not sure about OCR specifically, but the newer (past quarter) vision language models all have a lot of post training on detecting garbled text specifically. You can feed some of the old stable diffusion outputs into a modern model and they can figure out pretty reliably if the text gen is mangled. I think the feature is probably used as part of the RL for the image gen to correct for bad text rendering.

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

#208

Post by yorwba »

sandworm101 wrote: post #193
mynti wrote: 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

User-targeted fashion advice is the polite goal. AI designed to generate images of people is actually racing to capture the entertainment markets. They want to be ready to replace models/actors in everything from fashion mags to porn studios. That is where the money is.

For Alibaba, it's definitely all about shopping. That's where their money is. They haven't had much luck investing in entertainment so far.

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

#210

Post by R_D_Olivaw »

zarzavat wrote: post #116
DaiPlusPlus wrote: post #110

Earlier quoted context omitted.

…but the illustrative diagrams are a simulacrum; if you ask Qwen, or any image-generator, for an “accurate” poster-design featuring a representation of a model of an atom and explaining its constituent parts I expect you’ll get an imitation-airbrush rendering of red, blue, and grey table-tennis balls orbiting in perfect circles; you might get an electron-shell diagram if you’re lucky. What you won’t get is anything r…

This seems like something that could be solved by asking an LLM to write the prompt for the image model. You can also feed in the output of an image model into an LLM and ask it to check it/make improvements.

This is the way.

There's definitely more dogfooding that needs to be done. And id argue that if your purpose is truly to learn or to teach, the process of describing that image will do wonders for retention.

Post reply on HN