A character's identity and appearance are preserved while its motion and style are replicated from a reference video using motion-controlled generation.
Use the copy button above to grab the text exactly as written.
Drop it in unchanged since the camera, lighting and duration are already specified.
Change only the subject or setting for the most predictable result; the same wording carries over to other models too.
Sep 27, 2026
Sep 27, 2026
Sep 27, 2026
Sep 27, 2026
Sep 27, 2026
Sep 27, 2026Every claim below is measured against the 190 prompts in this library, not asserted.
'dynamic' is used by 6 prompts in the library, rank #22 of the camera terms seen here.
'-' appears in 0 prompts library-wide, rank #-.
9:16 is used by 33 of the 190 prompts in the library. Naming it at all matters more than which one is picked.
This prompt declares a consistency lock, which is what keeps a subject recognisable across a clip.
Seedance 2.5 accounts for 70.5% of the library (134 of 190 prompts).
Marked intermediate, based on how many specs it stacks (camera, lighting, duration, lock) at once.
