Letting neural networks be weird

  • About Me
  • Contact me
  • FAQ
  • Merchandise
  • Random
  • Archive
  • RSS

Dungeons and Dragons creatures, generated by neural network

The game Dungeons and Dragons has all sorts of lists of spells and abilities you can use for gameplay. I trained an algorithm called a recurrent neural network to generate more spells - like Barking Sphere, Hold Mouse, and Gland Growth. Then, with a larger set of spells in my training dataset, I trained a better neural net that generated even more - like Song of the Dave, Summon Ass, and Shield of Farts.

It turns out that in addition to spellbooks, Dungeons and Dragons also has monster manuals - books full of the names and descriptions of creatures that adventurers can encounter. Colin Fredricks, who created the RPG Sufficiently Advanced, was kind enough to send me the names of 2,205 creatures from the 2nd edition monster manual. 

As I had hoped, the neural network generated creatures that would probably be pretty awesome.

image

Owlborn
Cat, Stone
Vampire Bear
Kick Spirit
Hatfright
Purple Bird
Slug, Spectral
Wolf, Chromatic
Golem, Rain
Human, Crystal
Hound, Plant
Fish, Astro-
Wolfworm
Ogre, Space
Dog, Goblin
Serpent Shark
Mommy, Greater
Giant, Dunebat
Cloud of Chaos

It also generated some creatures that you should probably run from until you figure out what they are. (Though Dome Animal might simply be a cool turtle)

image

Brain, Fire
Horse (Spider, Brain
Undead Lake Man, Fire
Walfablang
Fraithwarp, Giant
Fish, Sun of
Lycanthrope, Wereladoo
Pat, Great, Space
Shadowstaffer
Spectral Woof Greepy
Jabberwont
Animal, Dome
Dwarf, Giant
Burglestar
Pigaloth
Beeple, Desert
Wendless Woll
Memeball
Marraganralleraith

There were 118 dragons in the original dataset, so of course the neural net liked generating new dragons. Some perhaps better-conceived than others.

image

Dragon, Death Seep
Dragon, Purple Fang
Dragon, Curple Lard
Dragon, Dead
Big Dragon
Will O’Dragon

And it generated new unicorns!

Unicorn, Fumble
Unicorn, Bat
Unicorn, Black Willow
Unicorn, Sith Sheet

These might be possible misses, though.

Man-Can
Barber
Beet
Skull
Feast, Stone
Peg, Brown
Kurt
Durp Snake
Golf
Vampire, Putter

Enter your email here and I’ll send you a few more creatures that wouldn’t fit in the main post. Including the legendary Bung Dragon!

I’m crowdsourcing a couple more D&D-related datasets - see below!

Also, I thought it would be fun to generate D&D character names for a future project. If you go to this form (no email required), you can enter your character’s name, race, and class. Once I have enough of these, I’ll give them to the neural network and see what happens. Edit: wow, over 10,000 responses so far! (Check them out at this link) Keep them coming!

I’m also collecting character backstories! Submit as many as you like. https://goo.gl/forms/ReInNw0Tz0mwzTLO2 I will post some generated character bios as soon as I can figure out a strategy that works better than this:

There was the prince of the sun. He was raised by the arcane arts and accepted him to become a fire work and the pig of the scorpions. He was in the blood of curious by the world to be a part of the church, really with the bartender.

    • #neural networks
    • #char-rnn
    • #Dungeons and Dragons
    • #d&d
    • #d&d monster
  • 3 months ago
  • 3936
  • Permalink
Share

Short URL

TwitterFacebookPinterestGoogle+

3936 Notes/ Hide

  1. karamicrabbit liked this
  2. unbuttonbubblez liked this
  3. ask-de-writer liked this
  4. nodensjr liked this
  5. homer-j-simpon liked this
  6. meriwethergrey liked this
  7. big-rad-green-dad liked this
  8. dalkomhann liked this
  9. bowtomypointlesswords liked this
  10. actuallysarahart liked this
  11. fortheloveofapirate liked this
  12. blue-r4ven reblogged this from atlas-the-worldbuilder
  13. blue-r4ven liked this
  14. bastardivorcedme liked this
  15. atlas-the-worldbuilder reblogged this from probablyspeculativebiorpgideas
  16. thoughtsfromaginger reblogged this from silvershears
  17. vaenire liked this
  18. egregiousderp liked this
  19. shiparmada reblogged this from lewisandquark
  20. hermanncrab reblogged this from lewisandquark
  21. pennayluvall reblogged this from last-august
  22. pennayluvall liked this
  23. ferenginar reblogged this from lewisandquark
  24. meteoricalhumming liked this
  25. wordswithkittywitch reblogged this from animate-mush
  26. quitealovelyfox reblogged this from animate-mush
  27. arcane-ethereality liked this
  28. animate-mush reblogged this from this-is-not-an-alias
  29. feed-the-roses liked this
  30. grimmhooke reblogged this from wilwheaton
  31. smegandtheheads liked this
  32. this-is-not-an-alias reblogged this from lewisandquark
  33. nine-tailed-cat liked this
  34. holywritingpromptsbatbruh liked this
  35. aceomega liked this
  36. guenstige-krankenversicherung liked this
  37. bewareofdragon liked this
  38. happygodless reblogged this from g3rmb0y
  39. powderedtoooastman reblogged this from rettaroo
  40. powderedtoooastman liked this
  41. st-elsaba liked this
  42. terrafag liked this
  43. anonynymouse2 liked this
  44. iamascaryhuman liked this
  45. shadehunter98 liked this
  46. cutefeyrad liked this
  47. dort reblogged this from pettyartist
  48. erathem liked this
  49. lewisandquark posted this
  50. Show more notesLoading...
← Previous • Next →

Portrait/Logo

About

I train neural networks, a type of machine learning algorithm, to write unintentional humor as they struggle to imitate human datasets. Well, I intend the humor. The neural networks are just doing their best to understand what's going on. Currently located on the occupied land of the Arapahoe Nation.
https://wandering.shop/@janellecshane

Twitter

loading tweets…

  • RSS
  • Random
  • Archive
  • Mobile
Effector Theme — Tumblr themes by Pixel Union