AI Weirdness: the strange side of machine learning

Tag: clip

Total 9 Posts
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,
It looks like a log of rice that's been rolled lightly in rainbow sequins.

In search of a unicorn cake

I've generated a lot of terrible unicorn cakes by this point. Last time I experimented with generating cakes, using CLIP's internet training to guide a couple of image generating methods. Around the time I posted my experiments, RiversHaveWings, who developed one of the most popular methods, came out with a
Generating images from an internet grab bag

Generating images from an internet grab bag

Still amazed by this: Here's CLIP+VQGAN (trained on internet photos and their accompanying text), prompted two different ways: "A car driving down a desert road in monument valley" A car driving down a desert road in monument valley"A car driving down a desert road in monument valley | dramatic
The art of asking nicely

The art of asking nicely

There are upsides to working with a neural net that trained on a huge collection of internet images and text. One is that, instead of ominous grey geometric blobs when it doesn't understand your prompt (there is a free interactive demo of AttnGAN here and it is a lot of
Lucid Deep Dreaming?

Lucid Deep Dreaming?

“Frodo Baggins delivering a pizza through the mines of Moria” Remember my attempts to get CLIP+BigGAN to generate candy hearts? Here’s what an alternative method, CLIP+FFT, does with the prompt “a candy heart with a message”. Rather than a single obsessively-scribbled-upon heart, we now have a vast
Curse your valentine with these candy hearts

Curse your valentine with these candy hearts

When I’ve generated candy heart messages before, they’ve been text only - definitely some assembly required. But methods of generating custom images from descriptions are getting better all the time. Could I use modern machine learning to generate new candy hearts? The answer is no. For the image
Searching for Bernie

Searching for Bernie

“Leaning Tower of Pizza”, BigGAN steered by CLIP using Big SleepI wrote earlier about DALL-E, an image generating algorithm recently developed by OpenAI. One part of DALL-E’s success is another algorithm called CLIP, which is essentially an art critic. Show CLIP a picture and a phrase, and it’ll
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.