Most of the ai image generation stuff I've seen from adobe feels late to party in terms of what you can do with open source tools. Where they do compete however is with tight integration, and I guess that's what matters the most to users in the end.

There are plugins for gimp that let you do image generation, inpainting and other things.

As far as what the post shows, it looks very much like current models that generate novel viewpoints of an object, but for illustrations. It might be doable to fine tune this for illustrations and simply vectorise the new viewpoint again. Though this will destroy any structure previously held in the object.

All I'm saying is that we have the tech to do even more than what adobe is doing, we just haven't put it nicely together yet.