At this point I'm wondering if A.I will reach a point where we can make simple animations as easily as these images before DC releases any official in game Judith content
Absolutely. We will have so much more than that.
Currently, text to image models are unimodal. That means they are only trained on images, which have their content associated to words.
The next step is to have multimodality. Models will be trained on images, but they will also learn from other types of data. They could learn from data gathered from photogrammetry so that the model can create 3d representation of concepts easily. They could learn for the skeletal movement of articulated concepts, such as human movement.
Integrating of all these different types of data, we'll be able to generate 3d worlds with characters living in them. In the style of SS if we want to. We'll be able to do everything.
There's just a bit of work to be done on multimodality, then we'll have it all.