121–130 of 145 posts
Earlier quoted context omitted.
It looks like the 10 first ones are mangas. I wonder if there is a pool of pictures the AI gets inspiration from
This is just a gallery of images uploaded to a Wordpress website
Cool! Please use this technology to make a 4K video of an infinite zoom through the art. i.e. generate an image frame, zoom in 1% near the center of the image, re-anneal the art to fill in missing resolution, repeat. It would be analogous to the infinite exploration of the Mandelbrot fractal set. It might help us intuit the black box of the algorithm as well if it reaches some periodic local minima and keeps reproduc…
I think AI is currently able to generate images I find pleasant to look at, but they have no impact on me beyond that momentary enjoyment. It is still decoration and not yet art, according to my personal definitions. When I can tell an AI to make an image about the Spanish Civil War and it produces Guernica, then I will be impressed in the way human artists impress me. And then we will have a powerful new tool to com…
This doesn't sound like it would be unrealistic. I think this can be partially solved by two systems: one that paints and one that finds the best painting to match a current event (in the form of a topic). The latter system could be trained on a set of paintings and corresponding topics or meanings, and then uses this training to match newly generated paintings to topics/meanings.
Congratulations on the project! This looks very similar to my project: https://art42.net I've used the higher resolution model 1024, and I also chosen to generate the picture in advance. It's expensive to generate them realtime.
This isn't live/dynamically generated, but if it was, what would be a good way of architecting it in a basic implementation? Say you keep the WordPress site, do you then just send a request to some endpoint that is served by python which keeps the model in memory for quick responses?
Earlier quoted context omitted.
The language on the landing page suggests that every time you click Try Now a new image is generated. > Click the button below for an AI-generated abstract painting. Built for artists, developers, and hobbyists. Really though there is a gallery of around 10,000 pngs on a Wordpress site. Fake it 'til you make it!
The fine-print at the bottom explains it: "On a Tesla T4, it takes on average 0.173 seconds per novel generation." I don't think you can expect someone to pay for T4 instance 24/7 for some hobby project.
Earlier quoted context omitted.
The fact that the link says “Try Now” instead of “next image” or something like that is implying that you are using the AI generation when you click the button.
Agreed. I think that the button gives the implication. I was focusing on the quoted part, but you're right.
Earlier quoted context omitted.
Seems like the author is a fan. https://1secondpainting.com/wp-content/uploads/2020/07/1.png https://1secondpainting.com/wp-content/uploads/2020/07/2.png https://1secondpainting.com/wp-content/uploads/2020/07/3.png https://1secondpainting.com/wp-content/uploads/2020/07/4.png
Likely they used transfer learning on an anime face model.