new blog is @ghxstxrt, please follow me there!
PUT YOUR BEARD IN MY MOUTH
Sweet Seals For You, Always

⁂
"I'm Dorothy Gale from Kansas"
let's talk about Bridgerton tea, my ask is open
hello vonnie
2025 on Tumblr: Trends That Defined the Year

izzy's playlists!
taylor price

★
occasionally subtle
Cosmic Funnies

JBB: An Artblog!
d e v o n
cherry valley forever
trying on a metaphor
$LAYYYTER

if i look back, i am lost

titsay
Alisa U Zemlji Chuda

seen from China
seen from South Africa

seen from United States

seen from Vietnam
seen from China

seen from T1

seen from United States

seen from South Korea

seen from United Kingdom
seen from United States

seen from United States
seen from Canada

seen from Malaysia
seen from Malaysia
seen from United Kingdom

seen from South Africa

seen from Netherlands

seen from Vietnam

seen from Singapore

seen from United States
@ghostdoodle-s
new blog is @ghxstxrt, please follow me there!
i came back so i could rub my greasy taagnus hands all over everyone
Alexander Wang Fall-Winter 2016
It is not the prettiest but here is a little chart I made of skin tones.
The idea is to eye-drop anywhere on the chart to get a unique skin tone instead of getting stuck in the loop of “white, tan, dark”.
USEFUL.
FLESH CLOUD EAGER TO ASSIST YOUR ART.
im thinking about remaking my art blog so things are more organzied
would anyone consider commissioning me for/donating around $30-35? like ive said, i’ll be home alone for the next two to three days with nothing to eat but eggs, oatmeal, and ramen. theres a few things to cook but i dont even have milk. i have commission info on @ghostdoodle-s (but i will point out that ***all prices are negotiable***) and my donation page is ko-fi.com/a860i1g
so i just reached 2.5k followers and wanted to do a giveaway bc wow thank you?
- 1 reblog to enter
- followers only
- 2 winners (prizes will be like art above)
ends june 4th (2 weeks from today)
art trade wihth @velociraptor-astronaut of their oc
Insignia Lucensium, Senensium, Pisanorum, Pistoianorum, Volterranorum, Aretinorum, Cortonensium, Borgo a S. Sepolcro (edited) - c. 1550-1555 - via BSB
Valeria: o3o ppppttppptptpptt Dax: !!! :O I cropped it too much but they’re holding hands
(don’t reblog if you’re n/s/f/w, d///d//l//g// or similar)
If you opened your PayPal account before you were 18, and there’s ANY evidence of this, SHUT DOWN YOUR ACCOUNT AND USE YOUR REAL INFORMATION FOR A NEW ONE IF YOU NEED TO.
NO JOKE
PAYPAL IS SHUTTING DOWN ACCOUNTS THAT WERE OPENED BEFORE YOU WERE 18.
Sharing this here because I know this will affect a LOT of artists here.
PLEASE share this, this is super urgent and I don’t want any of you losing your funds.
Which OC would say this?
[reads ur palm] hey… this line here means you think people who read your palms are really hot…….
When you make a really cute OC that you love but don’t know what to do with them:
snake……… on………… meeeee………… (snake on me)
snake…… meeeee…….. OOOOOOON (SNAKE ON ME)
New paint colors invented by neural network
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.
Pixel Commission for @faepuke of their oc Alex ✨