It's on page 14 of the technical report. They generate synthetic data by putting text on top of an image, apparently without taking the original lighting into account. So that's the look the model reproduces. Garbage in, garbage out.
Maybe in the future someone will come up with a method for putting realistic text into images so that they can generate data to train a model for putting realistic text into images.
If you think diffusing legible, precise text from pure noise is garbage then wtf are you doing here. The arrogance of the it crowd can be staggering at times
Maybe in the future someone will come up with a method for putting realistic text into images so that they can generate data to train a model for putting realistic text into images.