First of all, I’m not an art student/anatomy expert/seasoned professional so some of these methods might be pretty questionable and might not be the recommended way to go about drawing stuff
But anyway yeah here’s a bunch of things I bear in mind while drawing stuff and it helps to some extent. I learnt a bunch of these from some other art references online somewhere so I don’t claim credit for like discovering these amazing anatomical facts or something
Hey more tips:
If you want to improve within a short amount of time you can use this nifty tool online: http://www.quickposes.com/ It basically gives you a bunch of poses and you gotta draw them with a time limit and everything so I do that occasionally
Also I’ve got a weird obsession with drawing hands like they’re one of my favourite things to draw somehow so if you wanna practice hands real quick then here’s what I recommend:
Ask your friends to give you a random hand gesture and sketch it out or like look at your own hand in crazy new poses and just draw that
People often say to me: “You draw like some kind of inhuman machine. If I eat your brain, will I gain your power?” The answer is yes, but there is another way.
The key to precise drawing is building up muscle memory so that your arm/hand/fingers do the things you want them to do when you want them to do them. Teaching yourself to draw a straight line or to make sweet curves is just a matter of practice and there are some exercises you can do to help improve.
If you’re going to be doodling in class or during meetings anyway, why not put that time to good use?
So if you’ve ever picked out paint, you know that every infinitesimally different shade of blue, beige, and gray has its own descriptive, attractive name. Tuscan sunrise, blushing pear, Tradewind, etc… There are in fact people who invent these names for a living. But given that the human eye can see millions of distinct colors, sooner or later we’re going to run out of good names. Can AI help?
For this experiment, I gave the neural network a list of about 7,700 Sherwin-Williams paint colors along with their RGB values. (RGB = red, green, and blue color values) Could the neural network learn to invent new paint colors and give them attractive names?
One way I have of checking on the neural network’s progress during training is to ask it to produce some output using the lowest-creativity setting. Then the neural network plays it safe, and we can get an idea of what it has learned for sure.
By the first checkpoint, the neural network has learned to produce valid RGB values - these are colors, all right, and you could technically paint your walls with them. It’s a little farther behind the curve on the names, although it does seem to be attempting a combination of the colors brown, blue, and gray.
By the second checkpoint, the neural network can properly spell green and gray. It doesn’t seem to actually know what color they are, however.
Let’s check in with what the more-creative setting is producing.
…oh, okay.
Later in the training process, the neural network is about as well-trained as it’s going to be (perhaps with different parameters, it could have done a bit better - a lot of neural network training involves choosing the right training parameters). By this point, it’s able to figure out some of the basic colors, like white, red, and grey:
Although not reliably.
In fact, looking at the neural network’s output as a whole, it is evident that:
The neural network really likes brown, beige, and grey.
The neural network has really really bad ideas for paint names.
Gabe + McCree & Genji is a recipe for disaster like, they’ll be going out to get McDonalds at 3 am in full Blackwatch uniform and they’ll arrive back at the base laughing to themselves, joking that Jack′s hairline on the statue looks better
Then there’s Ana, sitting in the dark with her hands folded, wearing a t-shirt saying ‘The Ghost Watches’: Where have you three been?