OutputのTwitterイラスト検索結果。 3,062 件中 78ページ目

Art Stream Output #2 - Scars of the Past: Order and Chaos (Marchosias & Monomasa)

#watercolours #水彩 #LIVEAHERO #ラブヒロ #tokyoafterschoolsummoners #放サモ

Art Stream Output #1 - Typhon

#watercolours #水彩 #tokyoafterschoolsummoners #放サモ

Occasionally the outputs look like a wanted poster searching for evidence of a cryptid, like #4 here.

Perhaps 1 in every 50 outputs were completely alien, like #1. I think the preponderance of legs, trunks, and tails in the training data confused the AI, so it just made these tentacled horrors. Occasionally it was just a long snoot, like #3.

Most of the training images were side views, hence the recurrence of that same composition so often. However, I did have some bats, which are illustrated face-front, wings spread. That silhouette seems to have influenced a few of the outputs.

But... I must admit, the source data is really skewing how charismatic the outputs can be. Most of the time, it's trying to draw "realistic" versions of medieval illuminated marginalia. I'm surprised I didn't see a goat farting fire.

Mammals just don't have a lot of color variety, at least in the source data. There are so many voles, shrews, pachyderms, etc. It tends to make the outputs pretty bland in their coloring. The variety is more in where the head goes and how big it is.

@tomgara here's the output when you put "through meditation i program my heart to beat breakbeats and hum basslines upon exhalation" into the latest AI art generation models 😁

Loosening control on the outlines, the outputs from this color experiment begin to feel like chromatic smoke.
#javascript #art

*:･ﾟ✧*:･ﾟFEEDBACKS *:･ﾟ✧*:･ﾟ
-essay, earth sci worksheet & digi art making, division of algebraic expressions, script making
-rush and non rush outputs, thankyou for trusting🤎
#acadd_helper

*:･ﾟ✧*:･ﾟFEEDBACKS *:･ﾟ✧*:･ﾟ
-literary analysis, essay, digital art making, essay
-rush and non rush outputs, thankyou for trusting🤎
#acadd_helper

Today, at 20:00 UTC, it is @thekissprecise premint day.

Looking forward discovering my outputs!

https://t.co/hNsYl6YGSq

@TormanJeremy I create these collages using various bits and bits of GAN-AI output.

After another footnote explaining what a “modem” is, Hiram explains how he might actually be able to help Captain America, by scanning and correlating the emergency calls to look for patterns! And based on the output, I can see where this is leading…! #marvel #captainamerica

My art output has been super low due to work being busy, but I managed a sketch of an old WoW RP character who broke a lot of hearts back in the day~

training a DALL-E model to generate 90s anime aesthetic cities. trains up fast compared with a VQGAN transformer, this output is at mere 50 epochs. the big downside is you have to actually sort and classify your training data. sheesh, im making AIs so i DONT have to work hard

One of the quirks of v1.1 is that it crops tall images to the center square and trains on that. The result is lots of outputs that crop out the top and bottom of the bird's body. Here's a selection of BIG BORBS that are just too big for their frame. They cannot be contained.

ok so I might do something different for the flowers (they'll still be there in the final output but I don't wanna do them for now sob dhajkd)

Ocalypse
They're Benevolent
1/1
24 hour Auction 👁️
10 $XTZ minimum bid, last 1/1s from this series sold for 40+

Tradigital Collage made entirely with various bits and pieces of GAN-AI output cleaned up in Photoshop.

l i n k below

my very first adobe illustrator tutorial is now up on youtube! here's the final output of what i call "hourglass (with a twist)" ⌛️

🔗 https://t.co/A8FMkkdNDv

Tags:
[ #adobeillustrator #art #illustration #vector #artph ]