· 2 min read

Language arts 1.0

After many false starts and dead ends, I finally found a concept that would truly drive me insane. I finetuned my Code2000 symbol GAN model on a set of generated images.

These images consisted of the 1,000 most commonly used four-letter words in English. With the newly trained model, I generated some new ones.

If you would like to purchase one of these word worms, you can find them in NFT form at the Language Arts Marketplace. I can’t imagine why you would, but there it is.

Warning: I don’t know what happens if you stare at these for too long! Use at your own risk.

Samples

Generated image from March 8, 2021 at 18:17:04Generated image from March 8, 2021 at 18:16:17Generated image from March 8, 2021 at 18:19:01Generated image from March 8, 2021 at 18:16:39Generated image from March 8, 2021 at 18:18:00Generated image from March 8, 2021 at 18:17:27Generated image from March 8, 2021 at 18:18:30Generated image from March 1, 2021 at 14:52:32Generated image from March 8, 2021 at 18:18:11Generated image from March 8, 2021 at 18:17:48Generated image from March 8, 2021 at 18:18:51Generated image from March 8, 2021 at 18:19:14Generated image from March 8, 2021 at 18:17:16Generated image from March 8, 2021 at 18:16:52Generated image from March 1, 2021 at 14:51:52Generated image from March 8, 2021 at 18:16:28Generated image from March 1, 2021 at 23:00:06Generated image from March 8, 2021 at 18:18:41