Re:Qwen 3.0 Image Pro
by NBJack on Wednesday August 05, 2026 @12:01PM
(#49184705)
If I had a nickel for every model card, repo, or spec posted here that had zero samples of the actual output, I could probably start financing a rack of MI455Xs.
OpenAI does surprisingly well in this regard with their blog posts, and I'm more of an Anthropic fanboy. I wish most tech releases for AI were as well done as OpenAIs they actually showcase what they've built, honestly, if I had to compare it to another company, I wouldn't be surprised if former Apple employees are doing OpenAI's press briefings. Whoever does press briefings at Apple, they are worth their weight in gold.
Re:Qwen 3.0 Image Pro
by amelius on Wednesday August 05, 2026 @04:00PM
(#49188167)
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 3.0 Image Pro
by vunderba on Wednesday August 05, 2026 @12:24PM
(#49185028)
Given that Qwen Image 2 didn’t even get an open-weight release, I really doubt we’re going to see any kind of open release for it. They seem to have completely shifted over to proprietary models sadly.
Re:Qwen 3.0 Image Pro
by themanmaran on Wednesday August 05, 2026 @12:18PM
(#49184945)
Pretty annoying user experience trying to test out the model on the official Qwen site. You get an immediate popup with "Security Notice: For security purposes, please add a payment method" that blocks you from clicking anywhere.
Honestly if you're launching a new model, you should probably just make it free for the 24 hours after launch so people can test it out. Otherwise just wait till it's on openrouter.
Re:Qwen 3.0 Image Pro
by svachalek on Wednesday August 05, 2026 @12:54PM
(#49185499)
gpt-2-image has such a yellow tinge though. It stands out badly on nearly any screen. The image quality is great otherwise, but I generally prefer nano banana for its color balance.
Re:Qwen 3.0 Image Pro
by vunderba on Wednesday August 05, 2026 @12:56PM
(#49185535)
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:
Re:Qwen 3.0 Image Pro
by vunderba on Wednesday August 05, 2026 @03:23PM
(#49187667)
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.
Re:Qwen 3.0 Image Pro
by dragonwriter on Wednesday August 05, 2026 @07:40PM
(#49190550)
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 3.0 Image Pro
by vunderba on Wednesday August 05, 2026 @12:33PM
(#49185187)
As I’ve said before, I wouldn’t put a lot of stock in Arena’s scoring system. They have MAI Image 2.5 ranked above Gemini Nano Banana Pro, and maybe that’s true on paper but good luck using it. Microsoft’s censorship makes Google feel like the wild west by comparison.
They also have Meta’s Muse Image ranked above NB Pro, which is just patently absurd. In my own GenAI benchmark it only managed a lackluster 7 passes out of 15. Even the open‑weight Ideogram 4 scored higher than that.
For reference, here’s GPT‑Image‑2, NB Pro, and Muse compared:
Re:Qwen 3.0 Image Pro
by Eueudhsbsj32 on Wednesday August 05, 2026 @02:20PM
(#49186793)
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..
Re:Qwen 3.0 Image Pro
by tingletech on Wednesday August 05, 2026 @01:59PM
(#49186462)
When I tried to sign up for Qwen last month (after getting an ad on youtube), after entering my credit card for a "free" trial, Alibaba wanted me to upload a picture of my driver's license to be able to use it! I almost sold by BABA.
Re:Qwen 3.0 Image Pro
by jjcm on Wednesday August 05, 2026 @02:31PM
(#49186965)
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.
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.
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?
https://news.ycombinator.com/item?id=48989701
I am not a Sam Altman fan, but I do give him credit where its due, their press briefings are chef's kiss.
on the right-hand side, it says:
"Version Tag: MAJOR
Open Source: No
Updated: Jul 20, 2026"
Honestly if you're launching a new model, you should probably just make it free for the 24 hours after launch so people can test it out. Otherwise just wait till it's on openrouter.
Qwen lost some key people after 3.6 and it looks like we're seeing the consequences of that, or perhaps the cause.
https://arena.ai/leaderboard/text-to-image
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.
Here's a quick trend of the "piss filter" in the gpt image series:
https://imgpb.com/vCZidh
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
They also have Meta’s Muse Image ranked above NB Pro, which is just patently absurd. In my own GenAI benchmark it only managed a lackluster 7 passes out of 15. Even the open‑weight Ideogram 4 scored higher than that.
For reference, here’s GPT‑Image‑2, NB Pro, and Muse compared:
https://genai-showdown.specr.net/?models=nbp,g2,mi
If these were processors, I wouldn’t spend another hundred on the faster one…
Why would they want to deal with the amount of bad press they'll get for unsavory porn? Look at what happened to Grok.
Unless they see it as a way to stoke anti-AI sentiment in the west and further polarize us..
Yes, they're real Seedance, no refusals.
Or rather, Alibaba cloud is equivalent to google cloud or aws.
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.
Also, mind if I take it for my open-source bookstore SaaS?
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.