Open source text-to-image diffusion
This is the obligatory post playing with text-to-image diffusion models recently made very popular by tools such as OpenAI’s DALL-E 2 or Google’s Imagen.
If you ever want to try this out yourself, I highly recommend starting with this open-source implementation of stable diffusion.
Here is an image generated by the prompt:
an unsolvable problem, digital art
(The black boxes are NSFW content filtered out by the model.)
A bit more theory of stable diffusion is available here with some interesting research questions collected here.
