TailorGAN
Generating Infinite-Length Images with a Relatively Small-sized Conditional Generative Adversarial Network Variant

This project is still in its early stages, and I plan to continue it when time permits.
My primary goal is to create a GAN model with a simple and compact architecture capable of generating infinitely long images.
Here, I will only include the initial results. Once I achieve satisfactory outcomes, I will update this page with detailed information about the model.
First, a series of tests were conducted on the MNIST dataset:

Initially, I modified a simple fully connected conditional GAN based on my idea and explored various variations using the MNIST dataset.
Below, you will find a set of MNIST zeros, but some of the images are actually generated while the rest are from the MNIST dataset. So far, the results appear to be satisfactory:

As shown below, the initial attempts at generating infinitely long images did not yield satisfactory results:

In the subsequent trial with a new modification to the previous model, I obtained unusual yet improved results compared to the previous ones:

Next, I applied an other modification of the method to the CelebA dataset:

Here are some initial results obtained:


I plan to address the issues and provide more results in the near future.