Google Bard has the ability to describe images. But it turns out what you get depends a lot on how you ask.
I gave Bard this image and the prompt "Please describe this spooky Halloween scene". On the right is the image I got when I took the
Since 2019 I've generated October drawing prompts using the year's most state-of-the-art text-generating models. Every year the challenges are different, but this was one of the hardest years yet. Large language models like chatgpt, GPT-4, Bing Chat, and Bard, are all tweaked to produce generic, predictable
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
For a couple [https://www.aiweirdness.com/botober2021/] of
[https://www.aiweirdness.com/628160900506025984/] years
[https://www.aiweirdness.com/ainktober-a-neural-net-creates-drawing-19-09-26/]
now I've been using neural networks to generate daily drawing prompts. With
today's text-generating neural networks far too large to finetune on a list of
existing
I've amused myself before
[https://www.aiweirdness.com/this-is-the-openai-api-it-makes-spookily-20-06-11/]
by getting GPT-3 to change one kind of text into another. With just a few
style-change examples, I got it to change the Winnie the Pooh theme song
[https://kids.niehs.nih.gov/games/songs/movies/winnie-the-pooh-theme/index.htm]
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
One of my favorite things ever is when AI instructs people to do silly creative
things, and the humans gamely play along.
For a couple
[https://www.aiweirdness.com/ainktober-a-neural-net-creates-drawing-19-09-26/]
of Octobers [https://www.aiweirdness.com/628160900506025984/] now I've used
various AI models to generate daily #botober drawing
I’ve used neural networks to generate Halloween costumes in the past, but the
early ones struggled with their complete lack of context for the training data.
Why is Statue of Liberty a plausible costume yet Statue of Pizza isn’t
[https://aiweirdness.com/post/166814009412/a-neural-network-designs-halloween-costumes]
? Those neural networks,
Doing a Halloween party? Need to bring a festive food? Advanced artificial
intelligence is here to help.
After all, some say that large neural networks like GPT-2
[https://aiweirdness.com/post/185085792997/gpt-2-it-cant-resist-a-list], which
trained on huge collections of text from the internet, have therefore absorbed
huge amounts of the