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

Qwen Image 3.0 Pro

qwencloud.com

Post reply on HN
Print view View original

51–59 of 59 posts

Re: Qwen Image 3.0 Pro

#51

Post by jjcm »

I was playing with this a bunch when it dropped a week ago. It's a big step up over their prior model, but it's nowhere near gpt-image-2 at least for high density UI design. Photos are a solved domain in my eyes, so the real question is if it can do infographics/web design.

Here are some samples, each with the same prompt:

Cannabis site

gpt-image-2: https://image.non.io/9fbf3396-889a-445e-b51b-ab4468ded269.we...

qwen-3: https://image.non.io/b5061e30-fafa-496f-9dad-2071e9473998.we...

Bookstore site

gpt-image-2: https://image.non.io/7157afee-914e-4433-9d5e-e3d0c8d8b3a3.we...

qwen-3: https://image.non.io/9556857b-e6f3-4754-8958-74b2265d946f.we...

While it does text fairly well, the overall layout/aesthetics are simply behind.

Re: Qwen Image 3.0 Pro

#52

Post by theturtletalks »

jjcm wrote: post #51

I was playing with this a bunch when it dropped a week ago. It's a big step up over their prior model, but it's nowhere near gpt-image-2 at least for high density UI design. Photos are a solved domain in my eyes, so the real question is if it can do infographics/web design. Here are some samples, each with the same prompt: Cannabis site gpt-image-2: https://image.non.io/9fbf3396-889a-445e-b51b-ab4468ded269.we... qwen…

The bookstore design is really nice. Did you use diffui.ai?

Also, mind if I take it for my open-source bookstore SaaS?

Re: Qwen Image 3.0 Pro

#54

Post by dannyw »

Eueudhsbsj32 wrote: post #50
minimaxir wrote: post #39

Earlier quoted context omitted.

Minimax just released the weights for a video model ( https://huggingface.co/MiniMaxAI/MiniMax-H3 ) that apparently only has limited safeguards.

I forgot about that.. I'm surprised China allowed them to release that. Surely it will only increase the likelihood and severity of western restrictions on Chinese open models. Unless they see it as a way to stoke anti-AI sentiment in the west and further polarize us..

There's plenty of sites/APIs providing (actually) uncensored Seedance / Seedream models from ByteDance, which I find surprising too.

Yes, they're real Seedance, no refusals.

Re: Qwen Image 3.0 Pro

#55

Post by jjcm »

theturtletalks wrote: post #52
jjcm wrote: post #51

I was playing with this a bunch when it dropped a week ago. It's a big step up over their prior model, but it's nowhere near gpt-image-2 at least for high density UI design. Photos are a solved domain in my eyes, so the real question is if it can do infographics/web design. Here are some samples, each with the same prompt: Cannabis site gpt-image-2: https://image.non.io/9fbf3396-889a-445e-b51b-ab4468ded269.we... qwen…

The bookstore design is really nice. Did you use diffui.ai? Also, mind if I take it for my open-source bookstore SaaS?

Yea, the prompt was the expanded json the diffui harness uses. And re grabbing the designs, go for it.

I expaneded out the designs here - feel free to copy them for your agent to build: https://diffui.ai/app/canvas/95934269-5dc8-4145-a33a-d3a4dc2...

I'd recommend adding something like this to the copied prompt:

"Focus heavily on the angular cuts. Use image-to-svg to generate the hero graphics and also generate images of the hero graphics - let me choose between the two of them."

That should help steer the agent a bit and will give you some optionality for the hero graphics.

Re: Qwen Image 3.0 Pro

#56

Post by vunderba »

CamperBob2 wrote: post #43
vunderba wrote: post #34

Earlier quoted context omitted.

True but it’s at least addressable with some basic tone-mapping changes. It’s easier to correct an issue like this than to deal with an image that simply doesn’t follow your prompt. Here's a quick trend of the "piss filter" in the gpt image series: https://imgpb.com/vCZidh

Not a great test case, considering how much of the artwork in-distribution for that type of image will have age-yellowed lacquer.

Oh yeah, that’s a good point I’ll generate some images of a theoretical earth with a solar system bathed in the light of a K-type orange dwarf star instead. :)

I have some other examples of it as well that aren't going to be potentially contaminated by that late 18th century / early 19th century tintype-esque training data.

https://imgpb.com/vTUHo

Re: Qwen Image 3.0 Pro

#57

Post by amelius »

JacobAsmuth wrote: post #45
amelius wrote: post #27

Earlier quoted context omitted.

I prefer no samples over cherry picked samples, though.

Really? You prefer not to see the top end of the distribution? Why?

Because I don't like baby sitting an AI. Just tell me what it is capable of; not what it is capable of when I invest a lot of work into it myself. The whole point of an AI is that it does the work for me.

Re: Qwen Image 3.0 Pro

#58

Post by dragonwriter »

Invictus0 wrote: post #32
minimaxir wrote: post #16

Earlier quoted context omitted.

Everything is less good than gpt-2-image and I suspect that will be the case for awhile, until potentially Nano Banana Pro 2. However, cost is significantly lower in this case. A Pro image here is $0.04, a gpt-2-image high is $0.21 and lower resolution.

Gpt 2 image is unlimited on a chatgpt pro plan

Which makes it a clear price win if you already subscribe to Pro for some other reason, otherwise the price crossover where ChatGPT Pro unlimited beats the per-image pricing cited here is 80+ images/day.

Re: Qwen Image 3.0 Pro

#59

Post by theturtletalks »

jjcm wrote: post #55
theturtletalks wrote: post #52

Earlier quoted context omitted.

The bookstore design is really nice. Did you use diffui.ai? Also, mind if I take it for my open-source bookstore SaaS?

Yea, the prompt was the expanded json the diffui harness uses. And re grabbing the designs, go for it. I expaneded out the designs here - feel free to copy them for your agent to build: https://diffui.ai/app/canvas/95934269-5dc8-4145-a33a-d3a4dc2... I'd recommend adding something like this to the copied prompt: "Focus heavily on the angular cuts. Use image-to-svg to generate the hero graphics and also generate images…

Thanks for expanding the designs for it, they look great! I need nice storefronts for my open-source SaaS but 5.6 Sol has been making them look really generic. I tried Google Stitch but it was much of the same. I really like diffui, but is there a way for me to use in Codex directly?
Post reply on HN