Electronic_Ant2706

Diffusion Models have recently gained popularity in the field of image generation, with widely used products such as Stable Diffusion employing this approach and yielding impressive results. While GANs are also recognized for their efficiency, in what scenarios do I need to choose GANs over Diffusion Models and do GANs have any advantages compared to Diffusion Models in image generation?

Here are a few reasons I can think of:

• Diffusion Models take more time and larger datasets to train.
• To train a Diffusion Model project, one must have substantial computational resources (a lot of GPUs), compared to GANs.
• The codebases of some popular Diffusion Models projects are not open source.

I don't know if these are correct. As for the mathematical aspect, I'm not an expert in that area.

I'm trying to figure out the training process of a conditional GAN.

For example, consider a dataset like MNIST. I give the conditional vector to produce only the number 7 for both the generator and discriminator. In the following scenarios, the discriminator will classify which one is fake and which one is real:

1. The generator produces realistic numbers other than 7, such as a realistic number 9 ?
2. The samples from the MNIST dataset that are not the number 7 (i.e., other numbers) ?

Thanks for your help!

I know there are plenty of tutorials online, but most of them just skim through the topic and don't have much in detail, some of them even contradict each other. I have read the original paper, but very technical and difficult to understand as a newbie. Are there any tutorials that explain GANs in details but are still newbie-friendly? Thanks