But the images your network generates look nothing like MNIST digits. There is also no variance. For example, all 9s are identical.

For MNIST your model is sufficient. But it’s not structurally complex enough to generate more complex images, even if you scale it up.

[flagged]

Have you employed a dozen ethicists to go through the input and output to make sure it can't say any slurs? [EDIT] That's why small ones don't exist