calesthio
f45ae2f933
Incorporate the structured taxonomy from Lin et al. "Building a Precise Video Language with Human-AI Oversight" (CMU/Harvard, arXiv 2604.21718v2). The paper proves prompts structured around five aspects (Subject / Subject Motion / Scene / Spatial Framing / Camera) unlock controllable cinematography in fine-tuned video generation models. Off-the-shelf VLMs already nail subject and scene; the gains live in motion, spatial, and camera, which prompts routinely omit. Universal layer (skills/creative/video-gen-prompting.md, +125 lines): - 5-aspect prompt skeleton replaces flat formula - Camera movements regrouped (translation / rotation / lens-only) with dolly!=zoom, pan!=truck, bird's-eye!=aerial disambiguations - New primitive tables: camera height, camera angle, POV, lens distortion (fisheye vs barrel), focus / DoF (rack / pull / tracking), playback speed (6 modes), subject transitions - Order-matters and self-contained-prompt rules - Identity anchoring rule for multi-shot - Strict static-shot rule, anti-subjective callout, overlays-not-depth - Per-model word-count guidance Per-model guides (sora, veo, hunyuan, ltx, seedance): - Add the primitives each model honors literally - Word-count sweet spots per model - Strengthen seedance verbatim-identity and subject-transition guidance Pipeline directors (cinematic / explainer / animation scene-director, cinematic / explainer asset-director): - 5-aspect scene-plan checklist (per-pipeline adapted) - Overlays-not-depth callout - Pre / critique / post self-review loop for generation prompts Reviewer (skills/meta/reviewer.md): - CHAI critique-quality rules: accurate / complete / constructive - Critical findings now require a proposed_fix Storytelling, cinematic, broll, video-reference-analyst: - Anti-subjective rule (replace mood adjectives with visual causes) - Camera-intent-per-beat for script writers - POV column in stock-footage query templates - 5-aspect structured output mandatory for reference-video analysis skills/INDEX.md: video-gen-prompting marked as canonical 5-aspect spec.
4.3 KiB
HunyuanVideo 1.5 — Prompting Guide
Source: Tencent Prompt Handbook For universal vocabulary, see:
skills/creative/video-gen-prompting.md
Word count: Hunyuan 1.5 reads well at 80–200 words; doesn't reward 400-word essays.
HunyuanVideo Prompt Formula
Text-to-Video
Subject + Motion + Scene + [Shot Type] + [Camera Movement] + [Lighting] + [Style] + [Atmosphere]
Image-to-Video
Subject Motion Dynamics + Scene Motion Dynamics + [Camera Movement]
For I2V, focus on describing MOTION, not appearance (the image provides appearance).
HunyuanVideo-Specific Strengths
Lighting as Atmosphere
Tencent emphasizes: "Light is the soul of atmosphere."
Describe lighting with multiple dimensions:
- Style: soft, hard, neon, ambient
- Direction: side-lit, backlit, overhead, underlighting
- Quality: harsh spotlight, diffuse glow
- Shadows: long dramatic shadows, soft shadow edges
- Color temperature: golden hour warmth, cool daylight blue
- Reflections: wet surface reflections, metallic glints
Camera Movement Library
| Movement | Type | HunyuanVideo Prompt |
|---|---|---|
| Crane / Pedestal | Translation (vertical) | "camera rises vertically" |
| Truck / Tracking | Translation (horizontal) | "camera tracks left alongside subject" |
| Dolly In | Translation (push) | "camera pushes forward toward subject" |
| Dolly Out | Translation (pull) | "camera pulls back from subject" |
| Pan | Rotation (yaw) | "camera pans right across the scene" |
| Tilt | Rotation (pitch) | "camera tilts upward to follow the rocket" |
| Roll | Rotation (Z-axis / Dutch) | "camera rolls clockwise into a Dutch tilt" |
| Orbit | Circular | "camera orbits around subject" |
| Follow | Lock-on | "camera follows subject from behind" |
| Zoom | Lens-only (focal length) | "camera slowly zooms in on the figure" |
| Rack focus | Lens-only (focal plane, snap) | "rack focus from the foreground bottle to the figure in the background" |
| Pull focus | Lens-only (focal plane, gradual) | "camera shifts focus from foreground X to background Y" |
| Static | Fixed | "static camera, no movement" |
Focal-plane labels at start AND end of dynamic-DoF shots
Hunyuan benefits when both endpoints of focus-changing shots are stated. State where focus starts AND where it lands — don't leave one implicit.
Example: "shallow DoF; focus on the foreground bottle at start; focus pulls to the figure in the background by end."
Without both endpoints, Hunyuan often defaults to deep focus or holds on the wrong plane.
Style Keywords
Photorealistic / Cinematic:
- Film noir, hard sci-fi, cinematic photography
- Period drama, war documentary, nature documentary
Animation / Illustration:
- 2D animation, Japanese anime
- Watercolor painting, Chinese ink wash
- Low-poly 3D, pixel art
I2V Best Practice
When using image-to-video, the input image defines appearance. Your prompt should ONLY describe:
- How the subject moves
- How the environment changes
- Camera motion
Good I2V prompt: "The woman's hair blows in the wind as she turns to face the camera. Leaves scatter across the path. Camera slowly dollies in."
Bad I2V prompt: "A beautiful woman in a red dress standing in a forest" — this repeats what the image already shows.
Order motions temporally
Describe motion in temporal order; if multiple movements occur, separate them ("first the camera pans right, then tilts upward"). Hunyuan executes motion in the order it appears in the prompt — bundling two movements into one clause causes one of them to be dropped or blended.
Example (T2V)
A young woman in a flowing white dress walks barefoot along
a deserted beach at golden hour. She trails her hand through
the shallow surf, leaving ripples. Her hair catches the warm
side-light from the setting sun. Medium tracking shot, camera
follows alongside at knee height. Soft golden lighting with
long shadows stretching toward the camera. Cinematic
photography style, shallow depth of field. Peaceful,
contemplative atmosphere.
Example (I2V)
The cat stretches lazily, then leaps from the windowsill
to the floor. Dust motes scatter in the shaft of light.
Camera remains static, slight rack focus from window to
landing spot.