Here's a new AI that can generate the face of any character based on short, textual input.
Check out this cool new service that lets users generate visual content with the help of an AI called Artflow. The AI generates portraits based on short, textual input by the user. The machine learning system interprets submitted prompts into images. In short, all you have to do is write a short description of a character you desire to generate and the AI will generate one based on your description. According to the creators, the AI uses Generative Adversarial Networks as well as the CLIP model from OpenAI and does not use any existing images, so the chances of generating an exact copy of an existing image are practically zero.
Here are some of the results, posted on Artflow.ai Twitter account: