@hypit/hypit 0.0.1 → 0.1.0

package/packages/seedance-kits/README.md

@@ -0,0 +1,153 @@
+# `@hypit/seedance-kits`
+
+Data-only authoring Kits for recurring Seedance semantics. They are `TextTemplate` source modules,
+not model wrappers, Providers or new execution nodes.
+
+Import a selected public Source from the installed package, for example
+`@hypit/seedance-kits/speaker`. The package manager or active Distribution owns the installed
+version; Source Closure reads that Source and its relative dependencies without copying it into the
+video project or reaching through a physical `../../packages/...` path.
+
+Each Kit is rendered by the domain-neutral `text:Render` Surface. Its Text output then feeds one of
+the three low-level `@hypit/seedance` invocation modes. Reference media and duration remain
+ordinary explicit graph edges:
+
+```svml
+<import as="text" from="@hypit/text@1"/>
+<import as="seedance" from="@hypit/seedance@1"/>
+<import as="broll-kit" source="@hypit/seedance-kits/broll"/>
+
+<text:Render id="broll-prompt" template={broll-kit.broll-v1} recipe={recipes.broll}>
+  <text:Set name="story" text={copy.broll}/>
+</text:Render>
+
+<seedance:ReferenceVideo id="broll" model="mini" prompt={broll-prompt}
+  duration="5" resolution="720p" aspect-ratio="9:16">
+  <seedance:Reference image={scene}/>
+  <seedance:Reference image={product}/>
+</seedance:ReferenceVideo>
+```
+
+Speaker uses the same graph vocabulary. The Kit assumes `@image1` is the visible person and
+`@audio1` is the voice-timbre reference; it owns no media counting or generation wrapper:
+
+```svml
+<import as="speaker-kit" source="@hypit/seedance-kits/speaker"/>
+
+<text:Render id="hook-prompt"
+  template={speaker-kit.speaker-v1}
+  recipe={recipes.speaker.host}>
+  <text:Set name="dialogue" text={story.segment.hook.dialogue}/>
+  <text:Set name="action" text={hook-action}/>
+</text:Render>
+
+<seedance:ReferenceVideo id="hook-take" model="mini"
+  prompt={hook-prompt} duration="8"
+  resolution="720p" aspect-ratio="9:16" generate-audio="true">
+  <seedance:Reference image={presenter}/>
+  <seedance:Reference audio={voice}/>
+</seedance:ReferenceVideo>
+```
+
+## Choose a template
+
+Each import below has the prefix `@hypit/seedance-kits/`. The selected Source exports the listed
+template id. Its linked `.svs` file owns the exact fixed wording, default choices and allowed values.
+
+| Import suffix / template | Intended relationship and media references | Text slots |
+| --- | --- | --- |
+| `speaker` / [`speaker-v1`](kits/speaker-v1.svs) | One visible speaker: `@image1` is the character-and-scene view; `@audio1` is that speaker's voice. | Required `dialogue`; optional `action` |
+| `broll` / [`broll-v1`](kits/broll-v1.svs) | A silent visual micro-story; images appear in authored reference order, with their roles explained in the story. | Required `story` |
+| `podcast` / [`podcast-v1`](kits/podcast-v1.svs) | Two fixed views: images 1/2 show A/B, and audio 1/2 supplies their corresponding voices. | Required `dialogue`; optional `action` |
+| `call` / [`call-v1`](kits/call-v1.svs) | Image 1 shows A in the main tile and B in the inset; image 2 reverses them. Both are live views, with audio 1/2 for A/B. | Required `dialogue`; optional `action` |
+| `street-interview` / [`street-interview-v1`](kits/street-interview-v1.svs) | Images 1/2/3 are interviewer A, guest B and shared street setups; audio 1/2 is A/B. A holds the microphone. | Required `dialogue`; optional `action` |
+| `motion-reference` / [`motion-reference-v1`](kits/motion-reference-v1.svs) | Image 1 supplies the subject; video 1 supplies body motion, gestures and pose dynamics. | Optional `direction` |
+| `camera-reference` / [`camera-reference-v1`](kits/camera-reference-v1.svs) | Image 1 supplies the subject; video 1 supplies camera framing, lens, movement and photographic rhythm. | Optional `direction` |
+
+For example, `source="@hypit/seedance-kits/call"` imported as `kit` exposes `kit.call-v1`.
+Text slots use `text:Set`; scalar Recipe choices use the selected template's named axes. Reading the
+template reveals what each choice actually asks the generator to do. Rendering the Text Output as a
+Run Target lets an author inspect the assembled prompt without generating media.
+
+Speaker, B-roll, Podcast, Call and Street Interview expose prompt choices through their Text
+Templates. The examples above use author-chosen literal durations. Measure adopted speech with
+`hypit measure` first, then choose a duration within the selected model's declared range; there is
+no duration-estimation node on the generation route.
+
+## Recipe, dialogue and action
+
+The Recipe carries recurring choices exposed by the selected template. `dialogue` receives the
+Script Segment's `.dialogue` Text, retaining pronunciation and Role turns. Optional `action` supplies
+this passage's attitude, attention, interaction and any motivated cuts admitted by the Kit.
+Do not retype the complete spoken text into action or treat each Role turn as a required new Take.
+For B-roll, `story` carries the silent visual events rather than spoken dialogue.
+
+These files are reusable packaged authoring material. When one production needs a different prompt
+structure, author a project-local Text Template and import that Source explicitly rather than
+modifying the installed package. A Kit is not a Core restriction or a hidden media-generation wrapper.
+Reference order, duration, audio generation and output aspect ratio remain explicit on the model
+Surface. Setting a prompt option cannot create a media reference or execute a postprocess.
+
+## Speaker: edited UGC from one useful view
+
+For ordinary direct-to-camera social video, explicitly select
+`edit-rhythm: pause-trim-jump-cuts` as the starting rhythm. Read the Hypit Skill's Video direction page
+for the directing judgment, and the [Speaker template](kits/speaker-v1.svs) for the exact wording of
+its Recipe choices. Choose `performance` and `gesture` for the character's intended presence.
+
+Reuse the same person-and-scene image and voice for ordinary Takes belonging to one UGC performance.
+Each Take can begin from that shared reference and meet the others at a natural cut. There is no
+required previous-tail-frame chain. Independent generation follows the intended edited form.
+
+For example, a lively ranking host can use:
+
+```svs
+speaker.host {
+  composition-stability: strict-locked;
+  camera-motion: none;
+  edit-rhythm: pause-trim-jump-cuts;
+  performance: high-energy-ugc;
+  gesture: expressive;
+}
+```
+
+`edit-rhythm: pause-trim-jump-cuts` asks the model for an edited pause-trim rhythm at phrase boundaries.
+It is compatible with a fixed camera and active performance. The template uses `continuous-take`
+when `edit-rhythm` is omitted; select that value when the passage calls for a continuous
+shot. Actual speed changes, trimming or audio extraction are explicit media operations; selecting
+this Recipe does not perform them on the returned video.
+
+## Podcast: two views and living listeners
+
+`@image1` is Host A's view, `@image2` is Host B's view; `@audio1` and `@audio2` correspond to those hosts.
+If Script uses names such as GIRL and GUY, state their correspondence to A/B in action. One Segment
+can contain the entire short exchange. Choose speaker or reaction cuts for the conversation rather
+than splitting it into a generation per line.
+
+Derive a complementary host view from the first useful scene image. Product variations normally
+derive from each host's own view plus the product reference. Action can state the meaningful handoff
+and resulting possession. Silent listeners can adjust posture, glance down and look back up; they
+must not speak the partner's lines. A split-screen opening has a different layout from this two-view
+template and can use its own explicit prompt and combined reference image.
+
+## Street interview: three supplied setups
+
+The image order is interviewer A, guest B, shared two-person setup; the voice order is A, then B.
+The interviewer always holds the microphone, moving it between speaking positions. The guest does
+not take ownership merely because the microphone is extended toward them.
+
+Action chooses cuts among the supplied setups. Guest answers can favor the guest close view, brief
+neutral questions the shared view, and a meaningful interviewer reaction their close view. Small
+opening and closing actions can establish an encounter: the guest looks up from another activity
+as the interviewer approaches, and begins to leave after the final answer. These are examples of
+motivated direction, not mandatory actions on every request.
+
+## Keep gesture and scene direction readable
+
+Use attitude and a few decisive actions. Prefer an explanatory hand movement or emphatic gesture
+over exact numerical finger arrangements; speech or downstream graphics can state the number.
+Avoid exaggerated reactions or constantly moving every person simply to prevent stillness.
+
+For a multi-scene B-roll montage, `story` can name the references in scene order and give each a small
+action. Choose an edit language compatible with cuts. “Continuous within each scene” and “one
+continuous shot for the whole montage” ask for different results.

package/packages/seedance-kits/kits/broll-v1.svs

@@ -0,0 +1,52 @@
+<?svml using="@hypit/text/svs@1"?>
+
+<sheet version="1" id="broll-v1">
+  text-template.broll-v1 {
+    separator: paragraph;
+    default-material-mode: practical-real;
+    default-story-shape: single-moment;
+    default-edit-language: continuous-shot;
+    default-camera-language: reference-locked;
+    default-motion-intensity: readable;
+  }
+
+  text-template.broll-v1.block.base { kind: fixed; order: 10; text: "Create a silent B-roll micro-film using the provided reference image or images."; }
+  text-template.broll-v1.block.contract { kind: fixed; order: 20; text: "B-ROLL CONTRACT: create visual support footage. Focus on visible action, object behavior, camera movement, and editing rhythm. Visible people perform visual actions rather than speaking to camera."; }
+  text-template.broll-v1.block.reference { kind: fixed; order: 30; text: "REFERENCE CONTRACT: preserve the intended identity, product, UI, props, setting, lighting, texture, wardrobe, and composition from the reference images. Use the references in their authored order and follow the story's explicit description of each reference's role."; }
+
+  text-template.broll-v1.block.material { kind: axis; order: 40; parameter: material-mode; }
+  text-template.broll-v1.choice.material.practical-real { text: "MATERIAL MODE: practical real-world UGC footage with believable physical causality and a lived-in phone-camera feeling."; }
+  text-template.broll-v1.choice.material.screen-demo { text: "MATERIAL MODE: a practical filmed screen demo. Interface elements remain physically contained on the device screen."; }
+  text-template.broll-v1.choice.material.product-beauty { text: "MATERIAL MODE: product beauty footage focused on object presence, packaging, texture, tabletop detail, or studio product motion."; }
+  text-template.broll-v1.choice.material.proof-capture { text: "MATERIAL MODE: proof capture such as a website, certificate, receipt, review, chart, or credibility page, treated as visual evidence."; }
+  text-template.broll-v1.choice.material.stylized-vfx { text: "MATERIAL MODE: an intentional visual-effects metaphor used as an expressive explainer rather than practical documentation."; }
+
+  text-template.broll-v1.block.story-shape { kind: axis; order: 60; parameter: story-shape; }
+  text-template.broll-v1.choice.story-shape.single-moment { text: "STORY SHAPE: one continuous visual moment with a small readable change or payoff."; }
+  text-template.broll-v1.choice.story-shape.reaction-beat { text: "STORY SHAPE: stimulus, realization, then a clearly visible reaction."; }
+  text-template.broll-v1.choice.story-shape.process-demo { text: "STORY SHAPE: a stepwise demonstration whose practical stages remain legible."; }
+  text-template.broll-v1.choice.story-shape.before-after { text: "STORY SHAPE: a clear and visually legible contrast between before and after states."; }
+  text-template.broll-v1.choice.story-shape.montage-sequence { text: "STORY SHAPE: several short shots around one idea, each adding distinct evidence or feeling."; }
+
+  text-template.broll-v1.block.edit { kind: axis; order: 70; parameter: edit-language; }
+  text-template.broll-v1.choice.edit.continuous-shot { text: "EDIT LANGUAGE: continuous-shot timing; let the visual action play as one coherent moment."; }
+  text-template.broll-v1.choice.edit.jump-cut-beats { text: "EDIT LANGUAGE: crisp jump-cut beats, with each meaningful action stage landing cleanly."; }
+  text-template.broll-v1.choice.edit.match-cut-montage { text: "EDIT LANGUAGE: match-cut montage connecting similar framing, motion, or composition across shots."; }
+  text-template.broll-v1.choice.edit.insert-cutaway { text: "EDIT LANGUAGE: relevant detail cutaways such as hand, screen, product, face, or reaction."; }
+
+  text-template.broll-v1.block.camera { kind: axis; order: 80; parameter: camera-language; }
+  text-template.broll-v1.choice.camera.reference-locked { text: "CAMERA LANGUAGE: preserve the reference framing with minimal drift and let subject action carry the shot."; }
+  text-template.broll-v1.choice.camera.selfie-vlog { text: "CAMERA LANGUAGE: intimate selfie, mirror, or vlog phone camera with natural arm and camera bob."; }
+  text-template.broll-v1.choice.camera.handheld-follow { text: "CAMERA LANGUAGE: a handheld follow camera moving with the subject or object through space."; }
+  text-template.broll-v1.choice.camera.push-reveal { text: "CAMERA LANGUAGE: a motivated push, tilt, or reveal guiding attention to the key discovery."; }
+  text-template.broll-v1.choice.camera.product-macro { text: "CAMERA LANGUAGE: close product macro, orbit, parallax, or detail-focused movement."; }
+
+  text-template.broll-v1.block.motion { kind: axis; order: 90; parameter: motion-intensity; }
+  text-template.broll-v1.choice.motion.micro { text: "MOTION INTENSITY: micro motion only, prioritizing proof, product, or still-evidence clarity."; }
+  text-template.broll-v1.choice.motion.readable { text: "MOTION INTENSITY: readable action with clear movement that remains easy to understand."; }
+  text-template.broll-v1.choice.motion.lively { text: "MOTION INTENSITY: lively UGC body, camera, or object movement."; }
+  text-template.broll-v1.choice.motion.impact { text: "MOTION INTENSITY: high-impact physical or sensory motion such as splash, burst, or fast reveal."; }
+
+  text-template.broll-v1.block.hygiene { kind: fixed; order: 100; text: "SCREEN AND TEXT HYGIENE: add no subtitles, captions, floating words, labels, logos, or ad overlays. Referenced physical labels, screens, websites, and documents remain attached to their objects."; }
+  text-template.broll-v1.block.story { kind: slot; order: 110; slot: story; optional: false; label: "MICRO-STORY PROMPT:"; }
+</sheet>

package/packages/seedance-kits/kits/call-v1.svs

@@ -0,0 +1,55 @@
+<?svml using="@hypit/text/svs@1"?>
+
+<sheet version="1" id="call-v1">
+  text-template.call-v1 {
+    separator: paragraph;
+    default-framing: locked-view;
+    default-edit-language: speaker-cuts;
+    default-pacing: compact;
+    default-performance: natural-banter;
+    default-reaction: active-listening;
+    default-gesture: natural;
+  }
+  text-template.call-v1.block.base { kind: fixed; order: 10; text: "Create a realistic vertical edited two-person video-call clip from two final video-call interface reference images."; }
+  text-template.call-v1.block.reference { kind: fixed; order: 20; text: "REFERENCE CONTRACT: @image1 has Host A in the main tile and Host B in the picture-in-picture tile; @image2 reverses those roles. Preserve identity, outfit, rooms, lighting, webcam perspective, interface layout, borders, controls, and geometry."; }
+  text-template.call-v1.block.live { kind: fixed; order: 30; text: "LIVE TILE CONTRACT: both tiles are live feeds. The speaker has richer face and body action; the other participant stays silent but responsive."; }
+  text-template.call-v1.block.speaker { kind: fixed; order: 40; text: "SPEAKER MAP: follow A: and B: exactly. A: uses @image1 as the visible call view; B: uses @image2."; }
+  text-template.call-v1.block.voice { kind: fixed; order: 50; text: "VOICE MAP: Host A uses @audio1 and speaks only A: lines. Host B uses @audio2 and speaks only B: lines."; }
+
+  text-template.call-v1.block.framing { kind: axis; order: 60; parameter: framing; }
+  text-template.call-v1.choice.framing.locked-view { text: "FRAMING: preserve the exact baseline call layout, crop, scale, and tile relationship."; }
+  text-template.call-v1.choice.framing.soft-push-in { text: "FRAMING: use one subtle digital push-in inside the main tile, then return to baseline."; }
+  text-template.call-v1.choice.framing.emphasis-closeup { text: "FRAMING: use one modest emphasis close-up inside the main tile while preserving the call UI."; }
+
+  text-template.call-v1.block.edit { kind: axis; order: 70; parameter: edit-language; }
+  text-template.call-v1.choice.edit.speaker-cuts { text: "CUT PATTERN: speaker-following reverse views; the current speaker occupies the main tile."; }
+  text-template.call-v1.choice.edit.reaction-cuts { text: "CUT PATTERN: add brief listener-view reaction cutaways during longer explanations, then return to the speaker."; }
+
+  text-template.call-v1.block.pacing { kind: axis; order: 80; parameter: pacing; }
+  text-template.call-v1.choice.pacing.measured { text: "PACING: measured; each line finishes cleanly before a short natural response beat."; }
+  text-template.call-v1.choice.pacing.compact { text: "PACING: compact responsive handoffs with enough articulation for every line."; }
+  text-template.call-v1.choice.pacing.rapid-banter { text: "PACING: rapid banter with interruption-like momentum while remaining intelligible."; }
+  text-template.call-v1.choice.pacing.varied-emphasis { text: "PACING: compact overall, slowing slightly for important names, numbers, doubts, and payoffs."; }
+
+  text-template.call-v1.block.performance { kind: axis; order: 90; parameter: performance; }
+  text-template.call-v1.choice.performance.natural-banter { text: "PERFORMANCE: natural responsive video-call banter."; }
+  text-template.call-v1.choice.performance.high-energy { text: "PERFORMANCE: vivid, quick, expressive short-form video-call energy."; }
+  text-template.call-v1.choice.performance.calm-expert { text: "PERFORMANCE: composed, precise, trustworthy expert discussion."; }
+  text-template.call-v1.choice.performance.playful-skeptic { text: "PERFORMANCE: playful skeptical chemistry with teasing smiles and amused disbelief."; }
+
+  text-template.call-v1.block.reaction { kind: axis; order: 100; parameter: reaction; }
+  text-template.call-v1.choice.reaction.subtle-listening { text: "EXPRESSION: both tiles stay alive through tiny nods, eye focus, breath, and small changes."; }
+  text-template.call-v1.choice.reaction.active-listening { text: "EXPRESSION: both tiles track the conversation with nods, smiles, and readable facial shifts."; }
+  text-template.call-v1.choice.reaction.skeptical-reacts { text: "EXPRESSION: skeptical eyebrows, amused disbelief, tiny laughs, and attentive eye movement."; }
+  text-template.call-v1.choice.reaction.big-reacts { text: "EXPRESSION: lively surprise, laughter, disbelief, and recognition while remaining coherent."; }
+
+  text-template.call-v1.block.gesture { kind: axis; order: 110; parameter: gesture; }
+  text-template.call-v1.choice.gesture.restrained { text: "GESTURE: restrained on-camera body language with very small hand beats."; }
+  text-template.call-v1.choice.gesture.compact { text: "GESTURE: compact semantic gestures kept inside each tile."; }
+  text-template.call-v1.choice.gesture.natural { text: "GESTURE: natural open palms, small points, nods, and posture shifts."; }
+  text-template.call-v1.choice.gesture.expressive { text: "GESTURE: richer hand, shoulder, posture, and face changes within the call framing."; }
+
+  text-template.call-v1.block.hygiene { kind: fixed; order: 120; text: "AUDIO AND TEXTURE: clean dialogue and realistic screen-recorded call footage. Add no subtitles, captions, chat bubbles, notification cards, or readable overlays; preserve interface elements already present in the references."; }
+  text-template.call-v1.block.dialogue { kind: slot; order: 130; slot: dialogue; optional: false; label: "DIALOGUE SCRIPT TO DELIVER:"; }
+  text-template.call-v1.block.action { kind: slot; order: 140; slot: action; optional: true; label: "ACTION DIRECTION:"; }
+</sheet>

package/packages/seedance-kits/kits/camera-reference-v1.svs

@@ -0,0 +1,9 @@
+<?svml using="@hypit/text/svs@1"?>
+
+<sheet version="1" id="camera-reference-v1">
+  text-template.camera-reference-v1 { separator: paragraph; }
+  text-template.camera-reference-v1.block.subject { kind: fixed; order: 10; text: "Use @image1 as the subject and preserve the subject's identity, outfit, and physical features."; }
+  text-template.camera-reference-v1.block.transfer { kind: fixed; order: 20; text: "Replicate @video1's camera framing, lens choice, camera height, movement, and photographic rhythm, applying that camera language to the subject from @image1 in a coherent setting."; }
+  text-template.camera-reference-v1.block.exclude { kind: fixed; order: 30; text: "Do not copy @video1's subject pose or body action. Let the subject move naturally for the transferred camera treatment."; }
+  text-template.camera-reference-v1.block.direction { kind: slot; order: 40; slot: direction; optional: true; label: "ADDITIONAL DIRECTION:"; }
+</sheet>

package/packages/seedance-kits/kits/motion-reference-v1.svs

@@ -0,0 +1,9 @@
+<?svml using="@hypit/text/svs@1"?>
+
+<sheet version="1" id="motion-reference-v1">
+  text-template.motion-reference-v1 { separator: paragraph; }
+  text-template.motion-reference-v1.block.subject { kind: fixed; order: 10; text: "Use @image1 as the subject and preserve the subject's identity, outfit, and physical features."; }
+  text-template.motion-reference-v1.block.transfer { kind: fixed; order: 20; text: "Replicate the body motion, gestures, and pose dynamics from @video1 exactly. The subject from @image1 performs that motion in their own setting."; }
+  text-template.motion-reference-v1.block.exclude { kind: fixed; order: 30; text: "Do not copy @video1's camera framing or lens. Let the camera move naturally to capture the transferred action."; }
+  text-template.motion-reference-v1.block.direction { kind: slot; order: 40; slot: direction; optional: true; label: "ADDITIONAL DIRECTION:"; }
+</sheet>

package/packages/seedance-kits/kits/podcast-v1.svs

@@ -0,0 +1,55 @@
+<?svml using="@hypit/text/svs@1"?>
+
+<sheet version="1" id="podcast-v1">
+  text-template.podcast-v1 {
+    separator: paragraph;
+    default-framing: locked-view;
+    default-edit-language: speaker-cuts;
+    default-pacing: compact;
+    default-performance: natural-banter;
+    default-reaction: active-listening;
+    default-gesture: natural;
+  }
+  text-template.podcast-v1.block.base { kind: fixed; order: 10; text: "Create a realistic vertical edited two-person podcast clip from two final camera-view reference images."; }
+  text-template.podcast-v1.block.reference { kind: fixed; order: 20; text: "REFERENCE CONTRACT: @image1 is Host A's final camera view and @image2 is Host B's final camera view. Preserve both identities, outfits, room, lighting, props, camera sides, lens feel, and seating relationship."; }
+  text-template.podcast-v1.block.speaker-map { kind: fixed; order: 30; text: "SPEAKER MAP: follow the A: and B: dialogue order exactly. Only the host assigned to the current line moves their mouth; any listener cutaway remains silent."; }
+  text-template.podcast-v1.block.voice-map { kind: fixed; order: 40; text: "VOICE MAP: Host A uses @audio1 and speaks only A: lines. Host B uses @audio2 and speaks only B: lines."; }
+
+  text-template.podcast-v1.block.framing { kind: axis; order: 50; parameter: framing; }
+  text-template.podcast-v1.choice.framing.locked-view { text: "FRAMING: keep each host's baseline reference crop and scale."; }
+  text-template.podcast-v1.choice.framing.soft-push-in { text: "FRAMING: use one subtle push-in on an important phrase or reaction, then return to baseline."; }
+  text-template.podcast-v1.choice.framing.emphasis-closeup { text: "FRAMING: use one modest emphasis close-up, then return to the baseline view."; }
+
+  text-template.podcast-v1.block.edit { kind: axis; order: 60; parameter: edit-language; }
+  text-template.podcast-v1.choice.edit.speaker-cuts { text: "CUT PATTERN: stay on the host who is currently speaking."; }
+  text-template.podcast-v1.choice.edit.reaction-cuts { text: "CUT PATTERN: briefly cut to the silent listener during longer explanations, then return to the speaker."; }
+
+  text-template.podcast-v1.block.pacing { kind: axis; order: 70; parameter: pacing; }
+  text-template.podcast-v1.choice.pacing.measured { text: "PACING: measured turn-taking, readable articulation, and breathing room between thoughts."; }
+  text-template.podcast-v1.choice.pacing.compact { text: "PACING: compact immediate handoffs while each line remains a natural continuous take."; }
+  text-template.podcast-v1.choice.pacing.rapid-banter { text: "PACING: rapid banter with quick backchannel energy while every line remains intelligible."; }
+  text-template.podcast-v1.choice.pacing.varied-emphasis { text: "PACING: compact handoffs, slowing slightly for important names, numbers, doubts, and payoffs."; }
+
+  text-template.podcast-v1.block.performance { kind: axis; order: 80; parameter: performance; }
+  text-template.podcast-v1.choice.performance.natural-banter { text: "PERFORMANCE: natural podcast banter with warm eye focus and believable intonation."; }
+  text-template.podcast-v1.choice.performance.high-energy { text: "PERFORMANCE: vivid high-energy short-form podcast delivery."; }
+  text-template.podcast-v1.choice.performance.calm-expert { text: "PERFORMANCE: composed, precise, trustworthy expert discussion."; }
+  text-template.podcast-v1.choice.performance.playful-skeptic { text: "PERFORMANCE: playful skeptical chemistry with teasing smiles and amused disbelief."; }
+
+  text-template.podcast-v1.block.reaction { kind: axis; order: 90; parameter: reaction; }
+  text-template.podcast-v1.choice.reaction.subtle-listening { text: "REACTIONS: tiny nods, eye focus, breath, and small expression changes."; }
+  text-template.podcast-v1.choice.reaction.active-listening { text: "REACTIONS: readable nods, smiles, eye movement, and line-by-line facial shifts."; }
+  text-template.podcast-v1.choice.reaction.skeptical-reacts { text: "REACTIONS: skeptical eyebrows, amused disbelief, small laughs, and attentive eye movement."; }
+  text-template.podcast-v1.choice.reaction.big-reacts { text: "REACTIONS: strong but believable surprise, laughter, disbelief, and recognition."; }
+
+  text-template.podcast-v1.block.gesture { kind: axis; order: 100; parameter: gesture; }
+  text-template.podcast-v1.choice.gesture.restrained { text: "GESTURE: restrained podcast body language with very small hand beats."; }
+  text-template.podcast-v1.choice.gesture.compact { text: "GESTURE: compact semantic hand beats near the torso and table."; }
+  text-template.podcast-v1.choice.gesture.natural { text: "GESTURE: natural open palms, small points, nods, and posture shifts."; }
+  text-template.podcast-v1.choice.gesture.expressive { text: "GESTURE: richer hand, shoulder, posture, and face changes while staying coherent."; }
+
+  text-template.podcast-v1.block.action-contract { kind: fixed; order: 110; text: "ACTION PROMPT: optional segment direction controls specified lines, gestures, expressions, and timing."; }
+  text-template.podcast-v1.block.audio { kind: fixed; order: 120; text: "AUDIO AND TEXTURE: clean dialogue, natural room tone, stable faces and hands, microphones, props, and photoreal motion. Add no subtitles, captions, labels, UI text, or floating words."; }
+  text-template.podcast-v1.block.dialogue { kind: slot; order: 130; slot: dialogue; optional: false; label: "DIALOGUE SCRIPT TO DELIVER:"; }
+  text-template.podcast-v1.block.action { kind: slot; order: 140; slot: action; optional: true; label: "ACTION DIRECTION:"; }
+</sheet>

package/packages/seedance-kits/kits/speaker-v1.svs

@@ -0,0 +1,136 @@
+<?svml using="@hypit/text/svs@1"?>
+
+<sheet version="1" id="speaker-v1">
+  text-template.speaker-v1 {
+    separator: paragraph;
+    default-composition-stability: soft-locked;
+    default-camera-motion: none;
+    default-edit-rhythm: continuous-take;
+    default-performance: natural-explainer;
+    default-gesture: natural;
+  }
+
+  text-template.speaker-v1.block.base {
+    kind: fixed;
+    order: 10;
+    text: "Create a realistic vertical phone-shot talking-head video. @image1 is the visible speaker and scene reference. Preserve the person's identity, face, outfit, setting, lighting, lens feel, and broad composition. @audio1 is the speaker's voice-timbre reference.";
+  }
+
+  text-template.speaker-v1.block.script-contract {
+    kind: fixed;
+    order: 20;
+    text: "Deliver the supplied script exactly in order with clear lip-sync. The visible person speaks every line. Do not rewrite, summarize, add, remove, or reorder words.";
+  }
+
+  text-template.speaker-v1.block.composition-stability {
+    kind: axis;
+    order: 30;
+    parameter: composition-stability;
+  }
+
+  text-template.speaker-v1.choice.composition-stability.flexible-ugc {
+    text: "COMPOSITION: preserve the reference person and setup while allowing normal lively creator-video framing variation.";
+  }
+
+  text-template.speaker-v1.choice.composition-stability.soft-locked {
+    text: "COMPOSITION: keep the speaker in the same general region and preserve the reference composition, allowing natural posture changes and tiny crop or scale breathing.";
+  }
+
+  text-template.speaker-v1.choice.composition-stability.strict-locked {
+    text: "COMPOSITION: preserve subject placement, perspective, left-right orientation, background relationship, and framing envelope throughout the shot.";
+  }
+
+  text-template.speaker-v1.block.camera-motion {
+    kind: axis;
+    order: 40;
+    parameter: camera-motion;
+  }
+
+  text-template.speaker-v1.choice.camera-motion.none {
+    text: "CAMERA: hold a steady fixed framing.";
+  }
+
+  text-template.speaker-v1.choice.camera-motion.subtle-punch-in-return {
+    text: "CAMERA: use one subtle push-in on the most important phrase, then return smoothly to the original framing.";
+  }
+
+  text-template.speaker-v1.block.edit-rhythm {
+    kind: axis;
+    order: 50;
+    parameter: edit-rhythm;
+  }
+
+  text-template.speaker-v1.choice.edit-rhythm.continuous-take {
+    text: "EDIT RHYTHM: one continuous creator explanation with natural breath timing.";
+  }
+
+  text-template.speaker-v1.choice.edit-rhythm.pause-trim-jump-cuts {
+    text: "EDIT RHYTHM: polished pause-trim jump cuts at phrase boundaries while keeping the framing coherent.";
+  }
+
+  text-template.speaker-v1.block.performance {
+    kind: axis;
+    order: 60;
+    parameter: performance;
+  }
+
+  text-template.speaker-v1.choice.performance.natural-explainer {
+    text: "PERFORMANCE: natural explainer energy with clear eye focus, expressive eyebrows, small nods, and a friendly conversational rhythm.";
+  }
+
+  text-template.speaker-v1.choice.performance.high-energy-ugc {
+    text: "PERFORMANCE: vivid high-energy short-form delivery with expressive face changes on key words.";
+  }
+
+  text-template.speaker-v1.choice.performance.calm-authority {
+    text: "PERFORMANCE: composed, confident, precise, and trustworthy, with deliberate emphasis.";
+  }
+
+  text-template.speaker-v1.choice.performance.reactive-playful {
+    text: "PERFORMANCE: playful and reactive, with amused looks, quick smiles, skeptical eyebrows, and lively timing.";
+  }
+
+  text-template.speaker-v1.block.gesture {
+    kind: axis;
+    order: 70;
+    parameter: gesture;
+  }
+
+  text-template.speaker-v1.choice.gesture.restrained {
+    text: "GESTURE: restrained body language; let face, eyes, and voice carry the meaning.";
+  }
+
+  text-template.speaker-v1.choice.gesture.compact {
+    text: "GESTURE: compact explanatory hand movement close to the torso and inside the frame.";
+  }
+
+  text-template.speaker-v1.choice.gesture.natural {
+    text: "GESTURE: natural creator gestures such as open palms, small pointing beats, nods, and posture shifts where the script calls for them.";
+  }
+
+  text-template.speaker-v1.choice.gesture.expressive {
+    text: "GESTURE: richer hand, shoulder, and posture changes that support the spoken idea while remaining physically coherent.";
+  }
+
+  text-template.speaker-v1.block.hygiene {
+    kind: fixed;
+    order: 80;
+    text: "Keep face, hands, skin texture, lighting, and motion photoreal and stable. Add no subtitles, captions, labels, logos, UI text, floating words, or other readable on-screen text.";
+  }
+
+  text-template.speaker-v1.block.dialogue {
+    kind: slot;
+    order: 90;
+    slot: dialogue;
+    optional: false;
+    label: "SCRIPT TO DELIVER:";
+  }
+
+  text-template.speaker-v1.block.action {
+    kind: slot;
+    order: 100;
+    slot: action;
+    optional: true;
+    label: "ACTION DIRECTION:";
+  }
+</sheet>

package/packages/seedance-kits/kits/street-interview-v1.svs

@@ -0,0 +1,49 @@
+<?svml using="@hypit/text/svs@1"?>
+
+<sheet version="1" id="street-interview-v1">
+  text-template.street-interview-v1 {
+    separator: paragraph;
+    default-framing: soft-handheld;
+    default-pacing: compact;
+    default-performance: natural-street;
+    default-reaction: active;
+    default-gesture: natural;
+  }
+  text-template.street-interview-v1.block.base { kind: fixed; order: 10; text: "Create a realistic vertical street-interview clip from three final reference views."; }
+  text-template.street-interview-v1.block.reference { kind: fixed; order: 20; text: "REFERENCE CONTRACT: @image1 is interviewer A's final camera setup, @image2 is guest B's final camera setup, and @image3 is their final shared two-person camera setup. These three supplied setups are a closed shot set, not loose subject references: every authored shot selects exactly one of them as its complete frame, and cuts go directly from one supplied setup to another. Never invent a fourth camera position or pass through an intermediate framing. Within each selected setup, obey the FRAMING direction below. Preserve both identities, outfits, street location, props, microphone, lighting, camera sides, and spatial relationship."; }
+  text-template.street-interview-v1.block.roles { kind: fixed; order: 30; text: "ROLE MAP: A is the interviewer holding the microphone. B is the guest. Follow A: and B: exactly. A uses @audio1; B uses @audio2; only the current speaker moves their mouth."; }
+  text-template.street-interview-v1.block.microphone { kind: fixed; order: 40; text: "MICROPHONE CONTRACT: A always holds the same microphone. On A: lines it stays near A's mouth; on B: lines A naturally extends it toward B with realistic wrist, hand, and arm adjustments."; }
+  text-template.street-interview-v1.block.order { kind: fixed; order: 50; text: "Follow the authored ACTION DIRECTION in order for camera changes, performance, and physical interaction."; }
+
+  text-template.street-interview-v1.block.framing { kind: axis; order: 60; parameter: framing; }
+  text-template.street-interview-v1.choice.framing.locked-scene { text: "FRAMING: locked camera. Hold the selected reference setup as the exact complete frame, preserving its composition, crop, scale, camera height, angle, and lens feel. No handheld drift, push, pan, tilt, zoom, reframe, orbit, or transitional camera movement."; }
+  text-template.street-interview-v1.choice.framing.soft-handheld { text: "FRAMING: realistic tiny handheld sway and operator breathing inside the selected camera setup while preserving its composition and camera side. Never turn that movement into a new crop, angle, camera position, or transition between setups."; }
+  text-template.street-interview-v1.choice.framing.subject-push { text: "FRAMING: make one modest push toward the active speaker inside the selected camera setup, then settle back to that same supplied composition. Never create another angle or camera position."; }
+
+  text-template.street-interview-v1.block.pacing { kind: axis; order: 80; parameter: pacing; }
+  text-template.street-interview-v1.choice.pacing.measured { text: "PACING: measured question and answer delivery with a natural beat between thoughts."; }
+  text-template.street-interview-v1.choice.pacing.compact { text: "PACING: compact responsive handoffs while every line remains understandable."; }
+  text-template.street-interview-v1.choice.pacing.rapid-qna { text: "PACING: rapid street Q and A with crisp short-form momentum."; }
+  text-template.street-interview-v1.choice.pacing.varied-emphasis { text: "PACING: compact handoffs with important punchlines slowed slightly to land meaning."; }
+
+  text-template.street-interview-v1.block.performance { kind: axis; order: 90; parameter: performance; }
+  text-template.street-interview-v1.choice.performance.natural-street { text: "PERFORMANCE: curious interviewer and candid, spontaneous, believable guest."; }
+  text-template.street-interview-v1.choice.performance.high-energy { text: "PERFORMANCE: vivid, fast, charismatic short-form street energy."; }
+  text-template.street-interview-v1.choice.performance.calm-expert { text: "PERFORMANCE: composed thoughtful guest and visibly attentive interviewer."; }
+  text-template.street-interview-v1.choice.performance.playful-skeptic { text: "PERFORMANCE: playful skepticism, teasing smiles, reversals, and small laughs."; }
+
+  text-template.street-interview-v1.block.reaction { kind: axis; order: 100; parameter: reaction; }
+  text-template.street-interview-v1.choice.reaction.subtle { text: "REACTIONS: tiny nods, eye focus, breath, and small expression changes."; }
+  text-template.street-interview-v1.choice.reaction.active { text: "REACTIONS: visible nods, smiles, eye movement, and readable facial shifts."; }
+  text-template.street-interview-v1.choice.reaction.big { text: "REACTIONS: lively but realistic surprise, laughter, disbelief, and delight."; }
+
+  text-template.street-interview-v1.block.gesture { kind: axis; order: 110; parameter: gesture; }
+  text-template.street-interview-v1.choice.gesture.restrained { text: "GESTURE: restrained body language; face, voice, and microphone movement carry meaning."; }
+  text-template.street-interview-v1.choice.gesture.compact { text: "GESTURE: compact semantic beats near the body, bag, and microphone."; }
+  text-template.street-interview-v1.choice.gesture.natural { text: "GESTURE: natural open palms, small points, nods, and posture shifts."; }
+  text-template.street-interview-v1.choice.gesture.expressive { text: "GESTURE: richer hand, shoulder, posture, and face changes while preserving candid realism."; }
+
+  text-template.street-interview-v1.block.hygiene { kind: fixed; order: 120; text: "AUDIO AND TEXTURE: clean dialogue, natural outdoor room tone, stable faces, hands, microphone, and photoreal motion. Add no subtitles, captions, labels, cards, or overlays; preserve physical signs and text already in the scene."; }
+  text-template.street-interview-v1.block.dialogue { kind: slot; order: 130; slot: dialogue; optional: false; label: "DIALOGUE SCRIPT TO DELIVER:"; }
+  text-template.street-interview-v1.block.action { kind: slot; order: 140; slot: action; optional: true; label: "ACTION DIRECTION:"; }
+</sheet>

package/packages/seedance-kits/package.json

@@ -0,0 +1,24 @@
+{
+  "name": "@hypit/seedance-kits",
+  "version": "0.0.0-dev",
+  "license": "SEE LICENSE IN LICENSE",
+  "private": true,
+  "type": "module",
+  "exports": {
+    "./speaker": "./kits/speaker-v1.svs",
+    "./broll": "./kits/broll-v1.svs",
+    "./podcast": "./kits/podcast-v1.svs",
+    "./call": "./kits/call-v1.svs",
+    "./street-interview": "./kits/street-interview-v1.svs",
+    "./motion-reference": "./kits/motion-reference-v1.svs",
+    "./camera-reference": "./kits/camera-reference-v1.svs"
+  },
+  "files": [
+    "kits",
+    "README.md"
+  ],
+  "devDependencies": {
+    "@hypit/svs": "workspace:*",
+    "@hypit/text": "workspace:*"
+  }
+}

package/packages/seedream/README.md

@@ -0,0 +1,21 @@
+# `@hypit/seedream`
+
+Exact author/compute contracts and package-owned author Surfaces for Seedream image generation.
+
+The two modes are separate Surfaces and project the primary result to an ordinary image Artifact.
+This package defines what the author requested, not where it runs: API translation, credentials,
+retry and queue behavior belong to a selected Runtime Endpoint such as `@hypit/provider-kie`.
+
+The modes stay explicit in the source:
+
+```xml
+<seedream:TextImage id="scene" prompt={prompt} aspect-ratio="9:16"
+  quality="high" output-format="png" nsfw-check="true"/>
+
+<seedream:ReferenceImage id="variation" prompt={variationPrompt} aspect-ratio="9:16"
+  quality="high" output-format="png" nsfw-check="true">
+  <seedream:Reference image={scene.image}/>
+</seedream:ReferenceImage>
+```
+
+Prompt and every reference remain explicit graph inputs; the Runtime chooses no model on the author's behalf.

package/packages/seedream/package.json

@@ -0,0 +1,21 @@
+{
+  "name": "@hypit/seedream",
+  "version": "0.0.0-dev",
+  "license": "SEE LICENSE IN LICENSE",
+  "private": true,
+  "type": "module",
+  "exports": {
+    ".": "./src/index.ts"
+  },
+  "hypit": {
+    "activation": "./src/activation.ts"
+  },
+  "dependencies": {
+    "@hypit/artifact": "workspace:*",
+    "@hypit/generation": "workspace:*",
+    "@hypit/markup": "workspace:*",
+    "@hypit/model-kit": "workspace:*",
+    "@hypit/protocol": "workspace:*",
+    "@hypit/text": "workspace:*"
+  }
+}

package/packages/seedream/src/activation.ts

@@ -0,0 +1,12 @@
+import { createMarkupSurfaceHostFacet } from "@hypit/markup";
+import { seedreamComponent, seedreamDefinition, seedreamManifest, seedreamModuleRef,
+  seedreamMarkupSurfaces } from "./index.js";
+import { decodeSeedreamReferenceImageSurface, decodeSeedreamTextImageSurface } from "./surface.js";
+export const hypitPackage = { format: "hypit.node-package@1" as const, modules: [{ manifest: seedreamManifest }], components: [seedreamComponent], hostFacets: [
+  seedreamDefinition.hostFacet,
+  createMarkupSurfaceHostFacet({ module: seedreamModuleRef,
+    declaration: seedreamMarkupSurfaces.find((item) => item.name === "text-image")!, handler: decodeSeedreamTextImageSurface }),
+  createMarkupSurfaceHostFacet({ module: seedreamModuleRef,
+    declaration: seedreamMarkupSurfaces.find((item) => item.name === "reference-image")!, handler: decodeSeedreamReferenceImageSurface }),
+] };
+export default hypitPackage;