←back to thread

Efficient high-resolution image synthesis with linear diffusion transformer

(nvlabs.github.io)
220 points Vt71fcAqt7 | 4 comments | 16 Oct 24 14:56 UTC | HN request time: 0.597s | source
Show context
henning[dead post] ◴[16 Oct 24 19:15 UTC] No.41862727[source]▶
[flagged]
david-gpu ◴[16 Oct 24 20:51 UTC] No.41863751[source]▶
Do you believe that human artists should pay license fees for all the art that they have ever seen, studied or drawn inspiration from? Whether graphic artists, writers or what have you.
replies(2): >>41863881 #>>41865729 #
1. kadoban ◴[16 Oct 24 21:10 UTC] No.41863881[source]▶
Human artists get in copyright trouble if the spam out a copy of something they studied and sell it. The businesses using AI artists do not seem to.
replies(2): >>41864492 #>>41864676 #
2. ClassyJacket ◴[16 Oct 24 22:29 UTC] No.41864492[source]▶
Image generation models don't do that either
3. david-gpu ◴[16 Oct 24 22:51 UTC] No.41864676[source]▶
Artists who think that their copyright has been infringed upon are free to sue, just as they do when the alleged plagiarist is a human. I fail to see the difference.
replies(1): >>41868096 #
4. ben_w ◴[17 Oct 24 10:11 UTC] No.41868096[source]▶
Scale.

The cost of the electricity needed to create an image, was the cost of hiring someone on the UN abject poverty threshold to examine it for 10 seconds… with 2 year old models and hardware:

https://benwheatley.github.io/blog/2022/10/09-19.33.04.html

(There's also trademark issues; from the discussions, I think those are what artists actually care about even though they use the word "copyright").