I built an AI model to auto-generate Dominion cards. Here are the hilariously bad results.

• aitextgen

  19 1,826 1.8 Python

  A robust Python tool for text-based AI training and generation using GPT-2.

Then I ran that through the ai and got it to spit out cards that looked like that training data. I used aitextgen. So I let it run for like 4 hours and it thinks it has made 10,000 rows of cards. But some of these cards are duplicates to each other or to cards that already exist, or use a card name that already exists in the original game, or have like 20 '|' characters in one row, or have zero '|'. So I run a script to remove all of these cards like that, and I end up with like 2,000-4,500 cards that are "functional".

• InfluxDB

  www.influxdata.com featured

  Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.

  

Suggest a related project