Skip to content

armgit / hypit

Public Imported from GitHub
0

Clone any viral video with AI agents. Not just a script, the whole workflow: swap the face, the words, the B-roll, ship 100 variants in one command, and get your 100M views.

docs: direct takes to the fast tier by default

rponede4c72b59493
diff --git a/.agents/skills/hypit/references/playbooks/craft/generated-dependencies.md b/.agents/skills/hypit/references/playbooks/craft/generated-dependencies.md
index 0ef25523..a16f3308 100644
--- a/.agents/skills/hypit/references/playbooks/craft/generated-dependencies.md
+++ b/.agents/skills/hypit/references/playbooks/craft/generated-dependencies.md
@@ -52,6 +52,11 @@ Never generate video from a prompt alone. Without a first frame nothing fixes id
lighting or wardrobe, so the take can be reviewed against nothing and the next take can match
nothing. Use the shape that takes a first frame, or the shape that takes ordered references.
+Generate it on the fast tier — `model="fast"` for a Seedance take — unless the author named a model
+or the delivery genuinely needs a resolution only the top tier offers. Takes are regenerated more
+often than they are kept, so the tier multiplies the whole bill rather than one request.
+`seedance-directing.md` holds the model contracts.
+
## A short stretch is not a short take
An authored take stays inside the selected model's declared duration range — read the range from the
diff --git a/.agents/skills/hypit/references/playbooks/craft/seedance-directing.md b/.agents/skills/hypit/references/playbooks/craft/seedance-directing.md
index 3bf027ec..133967f6 100644
--- a/.agents/skills/hypit/references/playbooks/craft/seedance-directing.md
+++ b/.agents/skills/hypit/references/playbooks/craft/seedance-directing.md
@@ -32,8 +32,14 @@ than relying on an unstated assumption.
## Respect model contracts
-- Use model values `standard`, `fast`, or `mini`. `fast` and `mini` support only 480p/720p;
- `standard` also supports 1080p/4k.
+- **`fast` is the model, unless the author named another one.** Write `model="fast"` on every take
+ and do not reach for `standard` or `2.5` on your own judgement: a video is many takes, most of them
+ are regenerated more than once, and the top model multiplies the whole bill for a difference that
+ costs more to find than it is worth. Take an instruction to use a particular model literally when
+ one is given, and otherwise never raise the tier and never stop to ask which to use.
+- The other values are `standard`, `mini` and `2.5`. `fast` and `mini` support only 480p/720p;
+ `standard` also supports 1080p/4k, which is the one reason to name it — a delivery that genuinely
+ requires 1080p, recorded as the deliberate choice it is.
- Keep duration an integer inside the selected model's declared range, and read that range from the
model rather than from memory: they differ, and one accepts far longer takes than the others.
Invalid values fail closed.