AI Weirdness: the strange side of machine learning

Tag: clip

Total 18 Posts
A collection of mostly chipmunks, one acorn, and two lumpy froglike things

How to disappear a platypus

I was testing DALL-E 2 to see if it would be subject to some common incorrect assumptions about the sizes of things. For example if you asked people what size a kiwi bird is, they tend to assume it's a smallish bird, maybe around the size of a kiwi fruit.
Three guinea pig horse toys, stocky with guinea pig faces and guinea pig markings.

New AI-generated horsies

Recently I've been experimenting with DALL-E 2, one of the models that uses CLIP to generate images from my text descriptions. It was trained on internet text and images, so there's a lot it can do, and a lot of ways it can remix the stuff it's seen online. I
Teacups with mostly nonsensical messages written in, or sometimes on, the leaves.

Reading tea leaves

DALL-E (and other text-to-image generators) will often add text to their images even when you don't ask for any. Ask for a picture of a Halifax Pier and it could end up covered in messy writing, variously legible versions of "Halifax" as if it was quietly mumbling "Halifax... Halifax" to
A set of 8 somewhate misshapen eggs with colorful but confusing patterns and bands.

AI-generated easter eggs

How would AI decorate an easter egg? I've tried this before by training an image-generating model exclusively on pictures of easter eggs I decorated (they came out plain, if a bit wobbly). I decided to see what I would get using a model based on CLIP, which has trained on
A screenshot of the AI Weirdness 2021 Advent Calendar, with one of the doors highlighted

An AI advent calendar

When I was a kid I looked forward to opening advent calendar doors in December, although the pictures behind the doors were pretty forgettable. A bell. A snowflake. If you were lucky, a squirrel. So I thought I'd see if I can generate something a bit more interesting, with the
A vivid green and red landscape with wobbly jelly-like bushes.

Playing with Pixels

Here's "Ice Cream Planet Swirl", as generated by Pixray. Full prompt: Ice Cream Planet Swirl #8bit #pixelart. Colors are chocolate, minty green, and cream.Pixray uses CLIP, which OpenAI trained on a bunch of internet photos and associated text. CLIP acts as a judge, telling Pixray how much its images
How to haunt and unhaunt a house

How to haunt and unhaunt a house

What do you get if you instruct an AI to turn a house into the most haunted house in the world? What if you ask it for the LEAST haunted house? How does an AI know what "haunted" looks like, anyways? I did some experiments with CLIP+VQGAN (link and
Several lumps of olden cake covered with generous dollops of creamy frosting.

Neural networks vs the Bake-off technical challenge

There's this baking competition I really like, and one of the elements in every show is what they call the Technical Challenge. In the Technical Challenge, Great British Bakeoff contestants have to bake something they may never have seen before, based solely on a brief description and a very sparse
AI is based on math so it is correct

AI is based on math so it is correct

Since OpenAI released CLIP, trained on internet pictures and their nearby text, people have been using it to generate images. In all these methods - CLIP+Dall-E, CLIP+BigGAN, CLIP+FFT, CLIP+VQGAN, CLIP+diffusion - you come up with a text prompt, some algorithm presents its images to CLIP,
You've successfully subscribed to AI Weirdness
Great! Next, complete checkout for full access to AI Weirdness
Welcome back! You've successfully signed in.
Unable to sign you in. Please try again.
Success! Your account is fully activated, you now have access to all content.
Error! Stripe checkout failed.
Success! Your billing info is updated.
Error! Billing info update failed.