What do the included instructions ask the model to do?
Replace only the main foreground dancer with the adult in the uploaded photo. Use the photo to guide the face, hair, clothes and proportions. Follow the reference dance, camera movement, party setting and lighting while keeping the other guests. This is a generation instruction, not a promise of exact preservation.
How can I change the appearance of my result?
Choose the photo containing the person and outfit you want. A clear face and visible clothing give the model more information than a tightly cropped or obscured face. The example’s cowboy clothing is not added to every result.
Which settings can I change?
Choose Standard 480p for 50 credits or HD 720p for 100 credits, and choose whether to include the fixed BGM. The dance, approximately 8-second duration, 9:16 frame and reference scene are fixed.
Can I paste these instructions into a different AI tool?
The workflow needs both the identity photo and the original motion reference; a text prompt alone does not supply those inputs. Other tools may accept different inputs and produce different movement or scene details. This page explains Dime Baby’s included setup rather than selling a separate prompt.
More questions about this topic
Can I make the reference dance longer by editing a prompt?+
No. There is no prompt editor or duration control. Both available qualities target 8 seconds.
Will a prompt make me look exactly like the uploaded photo?+
No instruction can guarantee that. The photo guides identity and clothing, but generation can still change facial details, hands and motion.