docs(prompting): capstone threads quote the verbatim prompt clause that buys each region

This commit is contained in:
Vance Ingalls
2026-07-27 14:54:51 -07:00
parent bd8437f7e4
commit 8f2e0541da
17 changed files with 85 additions and 0 deletions
@@ -108,6 +108,11 @@ Quote the exact copy — unquoted names and titles get paraphrased (see [anatomy
**Capstone thread** — the [Level 7 film](/prompting/capstone)'s Material region docks a designed lower-third chip that renders *behind* the matted-out subject (0:280:36 below, cut from the film).
</Note>
This is the clause in the [full capstone prompt](/prompting/capstone#the-full-prompt-verbatim) that buys the piece — prompt language you can lift for your own video:
> […] the main **keywords of their own line — derived from the clip's transcription — land word-synced as huge display text BEHIND the cutout**, each keyword slamming in on its spoken moment with the subject's silhouette occluding it (the two-layer text-behind-subject plate) […] A designed lower-third chip renders behind the subject.
<video controls muted loop playsinline preload="metadata" src="https://static.heygen.ai/hyperframes-oss/docs/images/prompting/capstone-region-material.mp4" style={{ borderRadius: "0.5rem", marginTop: "0.75rem" }}></video>
*That clause, rendered — the region cut from the finished film.*
*Next: [Caption styles](/prompting/captions-catalog) — the same timed-block pattern, tuned to on-screen text instead of name cards and social replicas.*