Example 1 — single-image first-frame I2VA (brand film, base 3-section, English):

For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.

Core idea (integrated_multimodal_description)
6 seconds, 16:9. The young woman in <Picture 1> walks beside a vintage car parked on a desert highway at golden hour. She opens the trunk, takes out a black leather bag, shares a quiet beat with the man standing beside the car, then walks away with the bag. Keep her identity, hair, outfit, and lighting consistent.

[Shot 1] Live-action, cinematic, a medium-wide shot. The woman (identity, hair, white outfit, lighting all locked to <Picture 1>) stands beside the open trunk of the vintage car. The camera pushes in with small amplitude at slow speed. She lifts the black leather bag from the trunk, pauses to share a quiet look with the man by the car door, then turns and walks out of frame right, bag in hand. Golden-hour backlight, long lens, shallow depth of field.

Soundscape (overall_soundscape)
Warm desert wind, the soft metallic tick of the cooling engine, her footsteps on sand, the faint creak of leather.

Music (non_diegetic_music)
A single sustained warm guitar drone, slow swell, fades as she exits.

---

Example 2 — full-reference Ref2VA (six-section, English). Note: subject_definitions + summary (with [task-type] prefix) + retention_analysis (with fixed markers) + detailed_description (style opens BEFORE [Shot 1]).

subject_definitions (subject_definitions)
<Subject 1> is the young woman in <Picture 1>, with long dark hair, a blue cardigan, and a thin silver necklace.
<Subject 2> is the vintage convertible in <Picture 2>, a 1960s chrome-bumper roadster in faded red.
<Picture 1> is the first frame of [Shot 1], anchoring the woman's identity, hair, outfit, and lighting.
<Picture 2> is the keyframe for the car's model, color, and chrome detailing.

summary (summary)
[reference generation] The target video shows <Subject 1> walking beside <Subject 2> on a desert highway at golden hour, opening the trunk, taking out a leather bag, then walking away. <Picture 1> and <Picture 2> together define her appearance and the car.

retention_analysis (retention_analysis)
<Subject 1> (appears in [Shot 1]): fully_preserved - her identity, long dark hair, blue cardigan, and silver necklace are retained.
<Subject 2> (appears in [Shot 1]): fully_preserved - the roadster's model, faded-red paint, and chrome detailing are retained.
<Picture 1> ([Shot 1] first frame): fully_preserved - her appearance and the opening composition are retained.
<Picture 2> ([Shot 1] keyframe): fully_preserved - the car's model and color are retained.

detailed_description (detailed_description)
The target video is live-action, cinematic, with warm golden-hour backlight and a shallow depth of field.
[Shot 1] A medium-wide shot establishes <Subject 1> standing beside <Subject 2>, the faded-red roadster, on a desert highway. The camera pushes in with small amplitude at slow speed. She lifts a black leather bag from the open trunk, pauses to share a quiet look toward the man by the car door, then turns and walks out of frame right, bag in hand. Her identity, hair, outfit, and lighting stay consistent with <Picture 1>; the car's model and color stay consistent with <Picture 2>.

overall_soundscape (overall_soundscape)
Warm desert wind, the soft metallic tick of the cooling engine, her footsteps on sand, the faint creak of leather.

non_diegetic_music (non_diegetic_music)
A single sustained warm guitar drone, slow swell, fades as she exits.

---

Example 3 — last-frame L2VA (single shot, official alignment wording, English):

How the reference pictures align with the target video — <Picture 1> (from [Shot 1]) aligns with the 6.00-second mark of the target video.

Core idea (integrated_multimodal_description)
6 seconds, 16:9. Show how the scene could plausibly arrive at <Picture 1>: an intact drinking glass is tipped off a dark wooden table and shatters, settling into the exact broken arrangement of <Picture 1>.

[Shot 1] Live-action, cinematic, a close shot begins with an intact drinking glass near the edge of a dark wooden table, while the same hand and sleeve visible in <Picture 1> approach from the right. The camera pushes in with small amplitude at slow speed as the fingertips strike the rim. The glass tips, falls, and hits the floor with a sharp impact; cracks spread through it as fragments slide outward. Toward the end, the moving pieces lose momentum and settle into the exact broken arrangement, hand position, camera angle, lighting, and final composition established by <Picture 1>.

Soundscape (overall_soundscape)
Fingertips tap the glass before it scrapes across the tabletop, falls, and breaks with a sharp crash. Small fragments scatter and gradually stop sliding across the floor.

Music (non_diegetic_music)
A low electronic pulse at a slow tempo, ending immediately after the glass breaks.

Do not include
No people's faces, no on-screen text, no logos.
