Some of the recent image-generating models have this thing where they can fill in the blank parts of images. It's handy when you want to show them exactly how to give you more of the same. Like these animal emoji. See if you can tell which ones I
Please enjoy this advent calendar, generated and illustrated with the help of three machine learning models (GPT-3, DALL-E, and Midjourney)
Full door descriptions
1. Eggnog as far as the eye could see
2. The fantastical lion of Mor-Bollox
3. Saturated Red Turkeys.
4. Blue reindeer (they're bouncing)
5.
I don't dress my cat in costumes because, without even trying, I know she would
hate that.
But now I can use text-to-image generators like DALL-E2 to imagine what she
would look like in costumes. After all, even if it never saw my cat in a robot
costume
One of the things I'm enjoying about text-to-image generators like DALL-E2 is
how it has stuff about common brands in its training data, but it still manages
to completely garble them
[https://www.aiweirdness.com/ai-versus-your-corporate-logo/].
Please enjoy these DALL-E2 attempts at Halloween candy favorites.
Prompt: "Product
DALL-E 2 is very good at generating images to match text descriptions but I felt
like using DALL-E 2 to mess up some brands. Here's breakfast cereals!
"A box of lucky charms cereal on a grocery store shelf""A box of Froot Loops on
a
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
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
One thing I've noticed with image-generating algorithms is that the more of
something they have to put in an image, the worse it is.
I first noticed this with the kitten-generating variant of StyleGAN, which often
does okay on one cat:
alternative for shocked_pikachu.pngbut is terrible
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
[https://www.aiweirdness.com/the-terror-of-the-sea/] and it could end up covered
in messy writing, variously legible versions of "Halifax"
I recently started playing with DALL-E 2, which will attempt to generate an
image to go with whatever text prompt you give it. Like its predecessor DALL-E,
it uses CLIP, which OpenAI trained on a huge collection of internet images and
nearby text. I've experimented with a few