I would like to create illustrations quickly using text prompts. I have tried using DALL-E, which follows the prompt well enough, but the quality of the image details is not good. I have also tried Midjourney, which produces quality images, but doesn't draw exactly what I ask.
If it is possible to train a model to create such illustrations, what would it take? For example, what model should be used and how many samples would be needed?
I'm thinking of creating something like this. I doubt the AI can match the quality, but what I've tried so far isn't even close to this.
