zlacker

[parent] [thread] 8 comments
1. dvrp+(OP)[view] [source] 2025-07-31 14:06:18
Hello everyone.

I’m the Co-founder and CTO of Krea. We’re excited because we wanted to release the weights for our model and share it with the HN community for a long time.

My team and I will try to be online and try to answer any questions you may have throughout the day.

replies(4): >>jackph+mi1 >>mk_stj+ap1 >>cubefo+Vv2 >>Wester+Qj3
2. jackph+mi1[view] [source] 2025-07-31 22:16:05
>>dvrp+(OP)
Hi. Thanks for this. What is your goal of doing so? From a business standpoint. Or is it purely altruistic?
replies(1): >>dvrp+uk1
◧◩
3. dvrp+uk1[view] [source] [discussion] 2025-07-31 22:33:25
>>jackph+mi1
Haha-classic!

It’s simple: hackability and recruiting!

The open-source community hacking around it and playing with it PLUS talented engineers who may be interested in working with us already makes this release worth it. A single talented distributed systems engineer has a lot of impact here.

Also, the company ethos is around AI hackability/controllability, high-bar for talent, and AI for creatives - so this aligns perfectly.

The fact that Krea serves both in-house and 3rd-Party models tells you that we are not that bullish on models being a moat.

replies(1): >>wjrb+bn1
◧◩◪
4. wjrb+bn1[view] [source] [discussion] 2025-07-31 22:49:40
>>dvrp+uk1
I can say that it's definitely working on me! I hadn't heard of Krea before, and this is a great introduction to your work. Thanks for sharing it.
replies(1): >>cchanc+po1
◧◩◪◨
5. cchanc+po1[view] [source] [discussion] 2025-07-31 22:59:05
>>wjrb+bn1
People underestimate how much goodwill companies gain from pushing opensource stuff out, not just from word of mouth but even picking up users for their commercial offerings too, while i could run opensource and appreciate it in a lot of cases using API's from the companies that i like (mostly ones that do opensource stuff) tends to be easier for bigger stuff...
replies(1): >>yieldc+Gq1
6. mk_stj+ap1[view] [source] 2025-07-31 23:05:29
>>dvrp+(OP)
Any plans to get into working with the Flux 'Kontext' version, the editing models? I think the use cases of such prompted image editing is just wildly huge. Their demo blew my mind, although I haven't seen the quality of the open weight version yet. It is also a 12B distill.
◧◩◪◨⬒
7. yieldc+Gq1[view] [source] [discussion] 2025-07-31 23:16:49
>>cchanc+po1
(unless the code repository and history is embarrassingly bad, which is most repositories)
8. cubefo+Vv2[view] [source] 2025-08-01 11:44:50
>>dvrp+(OP)
Regarding the P(.|photo) vs P(.|minimal) example, how do you actually decide this conflict? It seems to me that photorealism should be a strong default "bias".

My reasoning: If the user types in "a cat reading a book" then it seems obvious that the result should look like a real cat which is actually reading a book. So it obviously shouldn't have an "AI style", but it also shouldn't produce something that looks like an illustration or painting or otherwise unrealistic. Without further context, a "cat" is a photorealistic cat, not an illustration or painting or cartoon of a cat.

In short, it seems that users who want something other than realism should be expected to mention it in the prompt. Or am I missing some other nuances here?

9. Wester+Qj3[view] [source] 2025-08-01 15:48:27
>>dvrp+(OP)
I need model for other language than english
[go to top]