Abstract: We present ControlNet, a neural network architecture to add spatial conditioning controls to large, pretrained text-to-image diffusion models. ControlNet locks the production-ready large ...
When generating test files, for example color test, I wonder if the text labels could be bigger, since the engraved text is about 1mm high, which I can't read. Maybe adding an input for text size ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback