I’m continuing my Valentine’s Day tradition of getting huge neural nets to
generate candy
[/this-time-i-didnt-train-a-neural-20-02-14?r=1lic4&utm_campaign=post&utm_medium=web&utm_source=copy]
heart
[/more-candy-hearts-by-neural-network-18-02-12?
“Leaning Tower of Pizza”, BigGAN steered by CLIP using Big SleepI wrote earlier about DALL-E [https://www.aiweirdness.com/the-drawings-of-dall-e/], an image
generating algorithm recently developed by OpenAI. One part of DALL-E
[https://openai.com/blog/dall-e/]’s success is another algorithm called
Now that it looks like 2020 is finally truly over, I thought I’d follow up on a
few of my favorite posts, especially the ones that have fun updates. Starting
with:
Headlines of 2020
[https://ai-weirdness.ghost.io/2020-headlines?r=1lic4&utm_campaign=post&utm_
What type of giraffe would you like today?
Last week OpenAI published a blog post previewing DALL-E
[https://openai.com/blog/dall-e/], a new neural network that they trained to
generate pictures from text descriptions. I’ve written about past algorithms
that have tried to make drawings to
“When a Billion Years Disappeared [https://www.youtube.com/watch?v=6R_NAV8Ieuo]”
“That Time It Rained for Two Million Years
[https://www.youtube.com/watch?v=_1LdMWlNYS4]”
“When Giant Scorpions Swarmed the Seas
[https://www.youtube.com/watch?v=1sQXTXbuLYo]”
One thing I like about the PBS Eons show