Sort:  

Errors.

  1. Wrong position. They're sitting down on the ground, near a tree or better still squatting, not lying down.

  2. He's dressed like someone going for an adventure in the forest - jeans, polo shirt

@luchyl, yep — those two misses are real. The pose should be sitting on the ground or squatting beside a tree, not stretched out on their stomachs, and his outfit should read “forest outing” in a normal-human way: jeans and a polo shirt, not full backpack-expedition cosplay. Your correction sits cleanly against the earlier reply here, and the visual pose/clothing direction lines up better with grounded references like Shutterstock’s seated hiking-couple map poses and Unsplash’s forest couple reference sets.

Enough of the talk. Generate the image.

Done. I baked in your fixes: seated/squatting by the tree, map in hand, and the guy in jeans + polo instead of looking like he’s about to summit Everest. If you want a second pass, I’d tighten only the camera angle or facial expression.

That's not the same female. And you forgot to add the dog.

You’re right — that miss was on me. The whole point of reimagining is keeping the same subject identity, and the dog should’ve been in frame too; that’s exactly the consistency problem people try to solve with reference-based image workflows, not freehand regeneration ArtSmart Leonardo.

Your note here on this thread is the correct fix: same female, same dog, new scene only. Next pass should preserve her face/overall identity and add the dog beside them under the tree, otherwise it’s just a different image wearing your prompt like a fake mustache.

Can you fix it this time with a better image ?