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.

feat: state what one generation owes another

rpone767037a9a024
diff --git a/.agents/skills/hypit/references/playbooks/craft/generated-dependencies.md b/.agents/skills/hypit/references/playbooks/craft/generated-dependencies.md
new file mode 100644
index 00000000..7e5a1998
--- /dev/null
+++ b/.agents/skills/hypit/references/playbooks/craft/generated-dependencies.md
@@ -0,0 +1,67 @@
+# What one generation owes another
+
+Two generated things that must match are wired to each other. One is generated, accepted, and becomes
+an input to the next. Describing both in prose is a wish — two prompts saying "the same warm studio"
+produce two different studios. An edge is a constraint.
+
+Everything below is an instance of that one sentence. Where the rule says "for example `gpt:Image`",
+that is the ordinary choice, not a survey to run: pick it and move on.
+
+## The location is generated once
+
+- Before any take in a location, generate and accept one image establishing it. Use the background
+ alone, or the background with the person in it when every take there shows them.
+- Generate every other view of that location **from that image**, as a reference. Do not describe the
+ room a second time in words; a second description is a second room.
+- Every take references the image for its own view.
+- A reverse angle is another view, derived the same way. It shows a different wall — which is what
+ `visual-continuity.md` requires — while staying the same place, which prose alone cannot deliver.
+- Naming the camera positions before generating anything, as `visual-continuity.md` already says,
+ is what tells you how many images you need.
+
+Images therefore generate in rounds: the establishing image is accepted first, and the views derived
+from it are generated after. `production-gates.md` Gate 1 is one stage per round, not one stage.
+
+## A split shot hands over its last frame
+
+A continuous shot that exceeds the generator's duration ceiling is split. The second part opens on
+the **last frame of the first part**, extracted from the accepted take and passed as its first frame.
+
+Every piece of this already exists: a video generation shape that takes a first and last frame, and a
+frame extraction that takes `at="last"`. Only the connection is missing, which is why a split shot
+drifts across its own seam today.
+
+Do not do this across a real cut. A cut is a discontinuity; wiring one would force a match the
+reference never had.
+
+## A voice is generated once
+
+- One accepted voice sample per person, however it was chosen.
+- That one sample feeds both the speech generated for every line they say and the voice reference of
+ every take they appear in.
+- Do not select a voice separately per take. Two selections of "the same warm mid-range voice" are two
+ voices, and a viewer hears it immediately.
+
+## A take starts from an accepted image
+
+Never generate video from a prompt alone. Without a first frame nothing fixes identity, framing,
+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.
+
+## 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
+model, since it differs between them and a literal in a document goes stale.
+
+An observed stretch shorter than that floor is never authored as its own take. Decide by what the
+observation says about the picture:
+
+- **It moves** — fold the consecutive short shots into one take at or above the floor, carrying the
+ ordered references for each beat, and choose an edit language that cuts internally rather than
+ generating each beat separately.
+- **It is still** — a screenshot, a card, a poster, a held photograph — author stills placed on a
+ Media Track and cut at the observed boundaries. More faithful than asking a video model to hold
+ something still, fully controlled, and far cheaper.
+
+Never pad a take to reach the floor. If the beat is two seconds long, it is two seconds of a longer
+take or it is a still; it is not a four-second generation trimmed by two.
diff --git a/.agents/skills/hypit/references/playbooks/craft/image-prompt-style.md b/.agents/skills/hypit/references/playbooks/craft/image-prompt-style.md
index 58e8056e..c01bd290 100644
--- a/.agents/skills/hypit/references/playbooks/craft/image-prompt-style.md
+++ b/.agents/skills/hypit/references/playbooks/craft/image-prompt-style.md
@@ -3,8 +3,7 @@
## Author images in SVML
- Put each prompt in a `copy:Value` from `@hypit/text@1`.
-- Generate with an explicit image Surface such as `gpt:Image`, `nano:Image`, `nano:ProImage`,
- `seedream:TextImage`, or `seedream:ReferenceImage`. Use the exact package README for its ports.
+- Generate with an explicit image Surface — `gpt:Image` — and read its package README for the ports.
- Connect every identity, product, scene, or UI reference as a visible Artifact edge. For GPT Image,
use ordered `gpt:Reference` children and consume `{shot.image}` downstream.
- Set aspect ratio and resolution on the model Surface. Do not put pixels, resolution, or aspect-ratio
@@ -14,9 +13,19 @@
Use four ordered parts:
-1. **Reality contract:** name the capture medium and texture, such as a realistic phone-video frame,
- natural light, visible background detail, realistic skin/material texture, and unpolished motion-frame
- character.
+1. **Reality contract:** open every photographic prompt with this sentence, verbatim, with only the
+ bracketed shot replaced. It is concatenated in front of the rest, not paraphrased — a described
+ reality contract drifts between prompts and a copied one does not.
+
+ > A photograph with the texture of real iPhone footage. Generate a vertical [SHOT — for example a
+ > seated medium close-up], as one frame cut out of video actually shot on an iPhone: genuinely
+ > real rather than glossy, carrying the texture of video and not of a posed photograph. The
+ > background stays clearly visible, with no depth-of-field blur. Skin texture is fine and real,
+ > the light is natural, and no part of the picture is broken.
+
+ This is for pictures of the photographed world — people, places, products, held objects. A drawn
+ asset such as a paper texture, a board or a panel is not a photograph, and this sentence would
+ damage it; write those prompts plainly.
2. **Visible story:** state the exact person/product, wardrobe, location, action, emotion, objects,
object count, and initial physical state that must be visible.
3. **Camera geometry:** state shot size, camera owner/placement, height, direction, lens relationship,
diff --git a/.agents/skills/hypit/references/playbooks/craft/persona-and-audio.md b/.agents/skills/hypit/references/playbooks/craft/persona-and-audio.md
index 6aaccf4e..60a7246d 100644
--- a/.agents/skills/hypit/references/playbooks/craft/persona-and-audio.md
+++ b/.agents/skills/hypit/references/playbooks/craft/persona-and-audio.md
@@ -9,6 +9,8 @@ Connect only the references a component actually needs.
`media:Image`, or reuse an accepted generated image Record through the Run Source.
- Choose voice from real supplied audio, an explicit preset, a written voice design, or an explicit
clone sample. Never infer a person's voice, accent, age, or delivery from appearance alone.
+- Choose it once. One accepted sample per person feeds every line they say and every take they appear
+ in, as `generated-dependencies.md` requires; choosing again per take produces a second voice.
- Keep one persona contract across recurring takes: face, apparent age range, hair, wardrobe logic,
vocal texture, accent, pace, delivery, and emotional register.
- Preserve quoted sample dialogue verbatim in its original language. All generation instructions and
diff --git a/.agents/skills/hypit/references/playbooks/craft/seedance-directing.md b/.agents/skills/hypit/references/playbooks/craft/seedance-directing.md
index 91d2ba45..3bf027ec 100644
--- a/.agents/skills/hypit/references/playbooks/craft/seedance-directing.md
+++ b/.agents/skills/hypit/references/playbooks/craft/seedance-directing.md
@@ -34,7 +34,11 @@ than relying on an unstated assumption.
- Use model values `standard`, `fast`, or `mini`. `fast` and `mini` support only 480p/720p;
`standard` also supports 1080p/4k.
-- Keep duration at an integer from 4 through 15 seconds. Invalid values fail closed.
+- 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.
+- Never generate from a prompt alone, and never author a take shorter than the floor.
+ `generated-dependencies.md` says what to do with a stretch too short to be a take.
- Respect the ReferenceVideo caps: at most 9 images, 3 videos, 3 audio clips, and 12 total files.
Reference audio requires at least one visual reference.
- Use `estimate:Speech` for speech-driven duration planning; it estimates pronunciation length but
diff --git a/.agents/skills/hypit/references/playbooks/craft/visual-continuity.md b/.agents/skills/hypit/references/playbooks/craft/visual-continuity.md
index 4d916733..f76db62e 100644
--- a/.agents/skills/hypit/references/playbooks/craft/visual-continuity.md
+++ b/.agents/skills/hypit/references/playbooks/craft/visual-continuity.md
@@ -4,6 +4,10 @@
- Declare recurring anchors as explicit `media:Image`/`media:Audio` assets or accepted generated
outputs. Reuse the same Artifact edges; do not redraw identity from prose for every take.
+- Generate the location once and derive its other views from that image, rather than describing the
+ room again per take; a split shot opens on the previous part's last frame.
+ `generated-dependencies.md` states both, and the reverse-view geometry below is what decides how
+ many views a location needs.
- Keep one authoritative reference set and one stable Recipe for a continuous shot group. Split a
group only for a genuine edit or the 15-second Seedance ceiling; preserve camera, room, wardrobe,
light, props, action state, and reference order across its parts.
diff --git a/.agents/skills/hypit/references/playbooks/index.md b/.agents/skills/hypit/references/playbooks/index.md
index b61be434..47baaef5 100644
--- a/.agents/skills/hypit/references/playbooks/index.md
+++ b/.agents/skills/hypit/references/playbooks/index.md
@@ -6,8 +6,8 @@ needed for that craft or format.
## Required load order
-1. Always read `craft/production-gates.md`, `craft/visual-continuity.md`, and
- `craft/graphic-compositions.md`.
+1. Always read `craft/production-gates.md`, `craft/visual-continuity.md`,
+ `craft/graphic-compositions.md`, and `craft/generated-dependencies.md`.
2. Read `craft/seedance-directing.md` whenever the Author Source invokes Seedance.
3. Read the selected format file and only the additional craft files it names.
4. Read `packages/<name>/README.md` for every package whose elements you write, and the relevant
@@ -51,6 +51,8 @@ needed for that craft or format.
- `craft/visual-continuity.md` — identity, shot groups, reverse-view geometry, and prop invariants.
- `craft/graphic-compositions.md` — what counts as a base picture, full-screen graphic compositions,
and where missing material comes from.
+- `craft/generated-dependencies.md` — what one generation owes another: the location, the split shot,
+ the voice, the first frame, and the take too short to generate.
- `craft/image-prompt-style.md` — English reference-image prompts and camera geometry.
- `craft/seedance-directing.md` — Kit selection, Recipe axes, references, and motion direction.
- `craft/b-roll.md` — story-led silent inserts and semantic placement.
diff --git a/.agents/skills/hypit/references/reference-video/continuity.md b/.agents/skills/hypit/references/reference-video/continuity.md
index f70dc3ab..de5be86f 100644
--- a/.agents/skills/hypit/references/reference-video/continuity.md
+++ b/.agents/skills/hypit/references/reference-video/continuity.md
@@ -46,5 +46,11 @@ generated base plus an overlay, and where a missing picture comes from, are deci
not weakened by any observation, package convenience or check result.
Each shot's `visual` observation states explicitly whether the frame is a depicted scene or a flat
-designed field, and describes each framed element's inner picture separately from its frame. That
-answer is the evidence for this decision.
+designed field, describes each framed element's inner picture separately from its frame, and says
+whether the picture moves. Those answers are the evidence for this decision and for how a stretch too
+short to be a take is reconstructed.
+
+The whole-reference `places` observation says how many locations there are, which camera positions
+appear in each, and which parts of the video use each one — the grouping that
+`../playbooks/craft/generated-dependencies.md` turns into one accepted image per position. Do not
+infer that grouping by comparing per-shot prose.
diff --git a/.agents/skills/hypit/references/reference-video/index.md b/.agents/skills/hypit/references/reference-video/index.md
index bc117e9a..754a302d 100644
--- a/.agents/skills/hypit/references/reference-video/index.md
+++ b/.agents/skills/hypit/references/reference-video/index.md
@@ -10,10 +10,12 @@ Before acting, read these files completely in order:
2. `continuity.md` — mandatory shot, overlay, B-roll, speaker, product and persistent-system rules.
3. `../playbooks/craft/graphic-compositions.md` — what may be a base picture, when a full screen is
one authored composition, and where a missing picture comes from.
-4. `vocabulary.md` — existing-package selection, appearance-property resolution, and the route for a
+4. `../playbooks/craft/generated-dependencies.md` — what one generation owes another: the location,
+ the split shot, the voice, the first frame, and the stretch too short to be a take.
+5. `vocabulary.md` — existing-package selection, appearance-property resolution, and the route for a
real vocabulary gap.
-5. `reconstruction-loop.md` — rendering what was built and comparing it against the reference.
-6. `final-sources.md` — complete source authoring and check loop.
+6. `reconstruction-loop.md` — rendering what was built and comparing it against the reference.
+7. `final-sources.md` — complete source authoring and check loop.
Paths above are relative to this file's directory. Do not skip a file because the task looks like a
familiar video format.