91–100 of 488 posts
I'm no artist.. though I'll admit i dabble, but is it just me or does everything that is generated in this seem to lack emotion ? I have seen some very impressive pictures but nothing that seems to "emote"
Human being never characterize the world with linear rules.
Earlier quoted context omitted.
What about using this tech for ideation and artists for production? You could use Stable Diffusion et al to create new characters based on a prompt, then farm the concept out to artists to produce individual works. Kind of like hiring a super expensive agency to design your new logo or brand identity, then using a stable of in-house designers to translate the concept into UI, ads, etc.
That’s where it’ll be truly disruptive. SD for ideation, humanity for the final product.
Any signals humans give (painting x is better than y) is another signal to encode. Take billions of such ratings and improve the AI’s taste to superhuman levels.
In short, anything that humans would add to artistically improve the outcome is just another signal to be encoded. It’s weird to write it, but artistic creativity is deciding what new pixels go where, which is a search problem (in a large search space) which AIs are apparently doing great at.
We have a bias: we’re humans, we must be important somehow! But it comes down to a bigger neural net eventually outperforming the one in our heads.
Quoted post unavailable.
https://waxy.org/2022/08/exploring-12-million-of-the-images-...
> we grabbed the data for over 12 million images used to train Stable Diffusion, and used his Datasette project to make a data browser for you to explore and search it yourself.
> Read on to learn about how this dataset was collected, the websites it most frequently pulled images from, and the artists, famous faces, and fictional characters most frequently found in the data.
LAION collected the images used to train Stable Diffusion:
> All of LAION’s image datasets are built off of Common Crawl, a nonprofit that scrapes billions of webpages monthly and releases them as massive datasets. LAION collected all HTML image tags that had alt-text attributes, classified the resulting 5 billion image-pairs based on their language, and then filtered the results into separate datasets using their resolution, a predicted likelihood of having a watermark, and their predicted “aesthetic” score (i.e. subjective visual quality).
I'm no artist.. though I'll admit i dabble, but is it just me or does everything that is generated in this seem to lack emotion ? I have seen some very impressive pictures but nothing that seems to "emote"
If by emotion you mean faces then that’s just a lot of data to fit in the model. The rest is up to the skill of the pilot. You can do a lot with color palettes for instance.
Earlier quoted context omitted.
Why do people keep bringing up copyright anyway? It seems pretty clear that the images being generated by StableDiffusion are transformative so it's protected under Fair Use. Am I missing something here?
I think that's wishful thinking. It's objectively a mechanical derivation based on many copyrighted works. In many cases it's going to reproduce some works with not that much transformation. What's a similar thing that has come before this? I can't think of any, this is very novel. You'd want to wait for some rulings before you jump to conclusions.
As far as I understand it, this is still considered copyright infringement in most IP law systems. (If the samples aren't cleared)
After using SD heavily for a week, I half agree with this. It is incredibly disruptive, and it's wild how much it accelerates the creative process. I'll give you that. But two things I've noticed: First, artists will still have a massive advantage over non-artists with this tool. A photographer who intimately knows the different lenses and cameras and industry terms will get to a representation of their idea much fas…
I've been trying to get it to draw a picture of a man trapped inside of a light bulb. Can anyone think of a prompt that works? It draws all sorts of freaky things featuring men and light bulbs but none with the former inside the latter.
I'm not really sure I know how to use these tools. I tried the following prompt: "elon musk giving donald trump a massage using pizza sauce instead of oil, in a majestic room filled with flowers and golden toilets" ...and the result was a crappy AI-generated picture of not-quite donald trump holding a terrible rendering of a pizza, and some hands sticking out of random places. There were some red flowers in the pictu…
"A cup on a plate".
And then replace cup for other objects. It generates nonsense pretty quickly. It seems most able to generate stuff close to something which already exists in a complete form. Sort of a pastiche machine.