OpenAI trained a neural network that they call DALL·E with a dataset of text and image pairs. So now the neural network can take text input and output random combinations of descriptors and objects, like a purse in the style of Rubik’s cube or a teapot imitating Pikachu.
Neural network creates images from text
Projects by FlowingData See All →
How Much We Eat vs. How Much We Need
On average, we use less energy as we age, and so we should eat less. We don’t always adjust soon enough though.
The Demographics of Others
I think we can all benefit from knowing a little more about others these days. This is a glimpse of how different groups live.
Fast Food Menu of Calories
How does the distribution of calories vary by fast food restaurant? Here’s a chart that shows all the menu items for ten of the biggest national fast food chains.