zlacker

[return to "Releasing weights for FLUX.1 Krea"]
1. lawles+yz1[view] [source] 2025-08-01 00:00:24
>>vmatsi+(OP)
How did you train while ensuring only images consensually acquired were used?
◧◩
2. whimsi+Zz1[view] [source] 2025-08-01 00:04:14
>>lawles+yz1
Likely the same way visual artists ensure that they only learn from images with permissive licenses.
◧◩◪
3. codedo+C02[view] [source] 2025-08-01 05:26:13
>>whimsi+Zz1
Human learning and computer processing millions of works are different things. I don't think any human artists have seen as many images as the developers used for training.
◧◩◪◨
4. 0x457+qz3[view] [source] 2025-08-01 16:47:03
>>codedo+C02
Only if you don't count artists with able eye(s) living their life?
◧◩◪◨⬒
5. throw1+8g8[view] [source] 2025-08-03 15:39:22
>>0x457+qz3
Looking at real things while living life is categorically different from viewing millions of artworks made by other artists. I can guarantee you that no artist has ever seen millions of artworks. This comment is not even bad-faith, it's just wrong.
◧◩◪◨⬒⬓
6. 0x457+gfb[view] [source] 2025-08-04 17:18:51
>>throw1+8g8
Are you telling me artists never get inspired by something they saw living their life? Only allowed to be inspired when specifically looking at other art?
◧◩◪◨⬒⬓⬔
7. throw1+isc[view] [source] 2025-08-05 01:41:41
>>0x457+gfb
You must not have responded to the right comment, because your comment is completely irrelevant to mine, as anyone with eyes and basic reading comprehension can see that I never said anything like that.
◧◩◪◨⬒⬓⬔⧯
8. 0x457+9Ni[view] [source] 2025-08-06 21:00:39
>>throw1+isc
> Looking at real things while living life is categorically different from viewing millions of artworks made by other artists

I don't see a difference.

◧◩◪◨⬒⬓⬔⧯▣
9. throw1+Nbj[view] [source] 2025-08-07 00:14:41
>>0x457+9Ni
You're factually incorrect, then. Objectively, those things are different, along every single relevant axis - from the psychological, artistic, moral, economic, and legal perspectives.

The vast majority of humans (>99.99999%) can tell that those things are different. The fact that you can't should be somewhat concerning.

◧◩◪◨⬒⬓⬔⧯▣▦
10. 0x457+phl[view] [source] 2025-08-07 17:19:48
>>throw1+Nbj
The fact that you don't understand that humans absorb a lot of knowledge just by existing is concerning (if I cared).

> The vast majority of humans (>99.99999%) can tell that those things are different.

Citation needed.

[go to top]