Show newer

Neural net generated ingredients list 

My hobby is getting neural nets to complete lists because even the advanced ones make it weird.

aiweirdness.com/gpt-3-it-cant-

Neural net generated food items to enjoy! 

Pixray generating "View from the end of the Thanksgiving Table"

Demo here: pixray.gob.io/text2pixel/

Pixray Swirl uses CLIP to generate each frame to match my prompt, starting from a shifted version of the previous frame.

Prompt here was "Straight trail leading past a jelly landscape with jello mountains

Come for the jellyfish, stay for the colossal jam jar.
aiweirdness.com/playing-with-p

After I gave it a few examples of changing one style of text into another, I got GPT-3 to draw on the vast knowledge encoded in its internet training and improve some common error messages.
aiweirdness.com/use-ai-to-impr

If I give it a few examples, I can get GPT-3 to change the style of a sentence. See how it improves my writing!

aiweirdness.com/how-to-improve

I decided to see what CLIP+VQGAN would do when I gave it a house and told it to make it haunted.

Original image:
commons.wikimedia.org/wiki/Fil
vs modified to better match the phrase "a haunted Victorian house"

ai generated british food 

I decided to give two neural nets a go at the Great British Bakeoff technical challenges. They did both much better and much worse than I had guessed.

aiweirdness.com/neural-network

I feel like we often don't acknowledge how very strange US grocery store names are. People just think it's normal to shop at a place called Big Bear or Giant Eagle or Piggly Wiggly.

So I used GPT-3 to add to a list of Perfectly Normal grocery stores.
aiweirdness.com/very-normal-gr

Because I so dearly love it when humans play along when computers ask for silly things, I have generated drawing prompts for !

I've managed to get GPT-3 to follow themes. Here's "animals". The rest are at this link:
aiweirdness.com/botober2021/

I asked an image generating AI to generate "Full moon - high res" three times, giving it the same grey circle as a starting point

It's easier to make an industrial demon than a unicorn cake? I experimented with @RiversHaveWings's new diffusion-guided CLIP method.

"industrial demon, matte painting, artstation HD"
"unicorn cake with golden horn and rainbow sprinkles"
aiweirdness.com/unicorn-cakes/

"How the hell did she knit this?"

I had so much fun talking to Alison Korleski on the Fiber Nation podcast about SkyKnit, my AI-generated knitting pattern project.
interweave.com/fiber-nation/ai

AI-generated cake 

There's no cake fail like an AI-generated cake fail.

I had CLIP+VQGAN attempt some classic showstopper cakes. Here's its "galaxy glaze cake"
aiweirdness.com/ai-cake-fails/

Used GPT-3 to figure out how to become viral on the birdsite.

Um

Quote toot with a meme of you in a situation that makes you say "god damn it"

aiweirdness.com/quote-tweet-if

Pretty striking the difference that a byline makes when asking CLIP+VQGAN to generate images.

"Internet infrastructure"
versus
"Internet infrastructure by James Gurney"

new post at aiweirdness.com!
aiweirdness.com/my-favorite-no

Tried to generate a chair made of beetle kill pine.

It's a wood with distinctive blue streaks, salvaged from trees killed by pine bark beetles. Turns out it was easier to get CLIP+VQGAN to generate the texture than the chair.

ai-weirdness.ghost.io/why-is-g

Asking CLIP+VQGAN to generate

"a car driving down a road in monument valley"

versus "A car driving down a desert road in monument valley | dramatic atmospheric ultra high definition free desktop wallpaper"

SAME TRAINING DATA
ai-weirdness.ghost.io/untitled

What fascinates me about generating images with CLIP is that it CAN generate depth and realistic textures, but only if you know how to ask for them.

"A herd of sheep grazing on a lush green hillside" alone

vs with "amazing awesome and epic" added
ai-weirdness.ghost.io/the-art-

Show older
Wandering Shop

The Wandering Shop is a Mastodon instance initially geared for the science fiction and fantasy community but open to anyone. We want our 'local' timeline to have the feel of a coffee shop at a good convention: tables full of friendly conversation on a wide variety of topics. We welcome everyone who wants to participate, so long as you're willing to abide by our code of conduct.