I was wondering if Unified-IO supports depth-to-image synthesis?

Thank you for sharing such a great work.

I'm currently including comparisons with your method in my paper. While the text-to-image and depth estimation tasks were easy to evaluate using the provided code, I found it difficult to reproduce the depth-to-image task.

So, I was wondering if Unified-IO supports depth-to-image synthesis?

Thank you in advance!