A simple generative AI tool can create video game maps, character models and emojis from a single-sentence prompt within milliseconds.
and Timothy Merino at New York University and their colleagues designed the system as a way of understanding how simple an AI model can be while still proving useful.
鈥淲e tried as a starting point to figure out the most naive, simple approach we could do for textbook map generation,鈥� says Merino. 鈥淚t was surprisingly effective.鈥�
Advertisement
The model was trained on databases of 882 game maps, 100 game sprites and 10,000 emojis, all of which were labelled with descriptions of what the images showed. 鈥淎ll of our datasets were fairly small, and that was by design,鈥� says Merino.
The labelling avoided listing the specific names of characters, instead describing Mario as 鈥渁 man with a moustache dressed in red鈥�, for example. Alternative labels were also created to train the model using GPT-4, the large language model behind ChatGPT.
The AI model itself uses a simplistic neural network that removes many of the modern developments that are powering the current generation of AI. For example, the network doesn鈥檛 include any feedback loops, meaning the information flows in one direction, from input to output.
Despite its simplicity, the system was able to produce accurate depictions of what was asked by users via text prompts, such as 鈥渁 grassy field with some flowers鈥�, 鈥渁n island of trees in the river鈥� or 鈥渁 flooded village鈥�.
The model shows what can be done with limited computing power, says Togelius. 鈥淎 lot of people are aware of the potential for AI changing how games work,鈥� he says. 鈥淏ut also, a lot of these things are just massive models that require massive amounts of data to train. This thing is trained on your home computer and runs on your phone, basically, in blazingly fast time.鈥�
arXiv
