There is a learning curve for sure. Not so much with the interface. That is as simple as can be. The trick is finding the right way to describe what it is you want it to produce. I think that is pretty much the key to all AI image generators.

One thing I didn't notice right away was the big difference in credits used for the Dall-E engine vs. Stable Diffusion. And depending on the prompts and what you're looking for, more credits doesn't necessarily translate into better results.

The price for what you get though can't be beat. For that reason I give it 5 tacos. It's not perfect, but the value for what you pay is outstanding