alt Hacker NewsHello HN,
This is Diego from Krea. Today we are announcing the open beta of Krea 3, our newest foundational image model.
In a nutshell, it’s a frontier image model in terms of quality, but at a fraction of the speed and a fraction of the price.
We will be releasing a more technical update, like we did with Krea 2 (https://www.krea.ai/blog/krea-2-technical-report), but this website shows the capabilities we focused on:
* Native regional edits
* Precise edits so that there is minimal area degradation pixel-wise
* Frontier image quality. Benchmarks still being worked on, but in our internal evals it seems a no-brainer replacement to NBP or GPT Image, both speed and cost-wise.
* Faster edits (AFAICK, this should unlock a pareto frontier for speed in frontier edit models).
In terms of future updates, the team is thinking about letting folks fine-tune Krea 3 (via LoRAs) and open-weights, but we’re still in the middle of launch hiccups and then we’ll revisit the next iterations.
Thanks!
Replies
Does this mean "thinking about" open weights in the sense of remaining work to do before releasing them, or is it whether to release them at all? hopefully it's the former, Krea2 was awesome because it was open
Why do all the "frontier" models still occasionally output images with the horrible ai texture tells? I'm surprised whoever made the front page let those ones in lol. My hypothesis is that it is either an unpatching or feature loss shortcut/artifact. Until then I have no hopes of ai generated images being viable for anything actually beautiful or creative
Ex. https://optim-images.krea.ai/https---s-krea-ai-k3-presets-20...
As a Krea2 local model enjoyer, your challenge is that on the $20 GPT plan you get a fairly good amount of Codex use and image gen. If I used Krea, it would be because I fine tuned/built a workflow on top of it to do something GPT image couldn't/wouldn't do. Maybe there's a market for the cheapest "good enough" bulk image gen model (spam? idk what the applications would be), but personally I'd say you should focus on workflow add-ons/one click fine tuning/etc that design companies can use to create assets with their custom "look" since the GPT-Image look will become blase from overuse.
Nice release! The 12B open-weight Krea 2 scored pretty well in my GenAI benchmark [1] on txt2img (6 out of 15) when I tested it back in June, so I’m looking forward to putting Krea 3 through its paces.
While Krea 2 was principally a text-to-image model, it seems like Krea 3 might be flipping that around? When I tried the beta a few minutes ago, I noticed a warning message saying that text-to-image was experimental at this point. Is the plan still to treat text-to-image as a first-class citizen, or is Krea 3 going to be more focused on being an editing model?
> but at a fraction of the speed and a fraction of the price
"at a fraction of the speed" is generally understood to mean that it is much slower, but I don't think that is what you are intending to say (considering the title and website claim it is multiple times faster)?
Just a heads up, the trial period the email you send out for new signups seems to be broken - which is making trying this out hard.
your email:
>I just unlocked a personal discount of 40% on your account, and switched Pro on for the next 3 hours so you can use it before you decide. It unlocks you all premium features as well as: ∞ No credit ceiling
But after using doing one round of three images with the beta, it won't let me generate another example. Trying to put a handful of tests through to compare to what we get from our current system on top of nano bannana pro.