A graduate of the Communication University of China, known under the pseudonym Ciaochaos, talked about his project to create “beautiful QR codes.”
Instead of leaving QR codes in their traditional form, ciaochaos came up with an interesting approach: use images generated by a neural network to read a QR code and overlay parameters on them.
This is an idea he has wanted to implement for a long time, but the right tools have only recently emerged with the development of neural networks for image generation.
To create this QR code generation model, ciaochaos used Stable Diffusion technology and also developed the ControlNet model to improve the performance of the neural network. In this process, he was supported by his colleagues and professors from the university.
After training the model, it applied various combinations of checkpoint and LoRa methods to fine-tune the fabrication parameters to obtain QR-coded images.
You can see the final result of their work on the cover of this news. It looks impressive and much more interesting than standard codes of this type.
Source: Ferra
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
