subject_definitions: <Subject 1> is the young woman in <Picture 1>, with fair skin, long straight black hair with light bangs, and a high bun decorated with white flower hairpins and long beaded tassels falling beside her ears, wearing a pale mint-green hanfu with sheer layered sleeves and a white inner skirt, all softly lit by warm lantern light. <Picture 1> is the front-view identity anchor for <Subject 1>; use it for the face, hair, and costume. <Picture 2> is a character turnaround sheet showing the SAME single person from three angles (front, side, back) — the three figures are ONE person, not three different people; use it only for hair ornament and sleeve details. <Picture 3> is the exact last frame of the previous clip — the opening frame of this clip MUST be identical to <Picture 3> in face angle, expression, mouth state, head tilt and lighting. <Video 1> is the complete previous 11-second clip; this clip is its seamless continuation — same camera, same swaying rhythm, same singing continuation. <Audio 1> is the reference song, exactly the part to lip-sync from 00:00.000 to 00:11.000. summary: [video continuation + audio reuse] Continue seamlessly from <Video 1>: the same vertical extreme close-up of <Subject 1> in a classic Hong Kong wuxia-cinema look: moody low-key lighting, dramatic chiaroscuro on the face, warm amber lantern glow against deep teal-shadowed edges, faint drifting smoke and dust in the air, subtle film grain, cinematic teal-and-amber color grade, dark atmospheric backdrop softened by haze; her lips move in perfect syllable-by-syllable sync with the singing in <Audio 1>, every mouth shape matching the song for the entire clip from 00:00.000 to the end, with no drift and no gap. The first frame is exactly <Picture 3> (the last frame of <Video 1>), then the clip flows on with the same face, framing, gentle sorrowful melancholy expression, and soft swaying motion, camera unchanged, no cut, no jump. retention_analysis: <Subject 1> (appears in [Shot 1]): fully_preserved - face, hair, and mint hanfu stay identical to <Picture 1>. <Picture 1>: fully_preserved - identity only. <Picture 2>: partially_preserved - hairpin and sleeve details. <Picture 3> ([Shot 1] first frame): fully_preserved - the opening frame must reproduce this exact frame: same angle, same mouth, same expression, same light. <Video 1> (continuation source): attribute_transfer - the motion, swaying rhythm, singing tempo and camera stay identical; this clip begins on its exact final frame. <Audio 1>: fully_copy - the reference audio drives the lip-sync for the entire 11-second clip; every syllable is matched from 00:00.000 to 00:11.000, no drift. detailed_description: [Shot 1] Photorealistic. Vertical 9:16, classic Hong Kong wuxia-cinema look: moody low-key lighting, dramatic chiaroscuro on the face, warm amber lantern glow against deep teal-shadowed edges, faint drifting smoke and dust in the air, subtle film grain, cinematic teal-and-amber color grade, dark atmospheric backdrop softened by haze. Extreme close-up. This clip begins EXACTLY on <Picture 3> — the last frame of the previous clip — with the identical face angle, identical mouth position, identical expression, identical head tilt and identical lighting, then continues as one seamless shot with no cut, no jump, no reset. 00:00-00:11.000: The camera holds the same static extreme close-up on <Subject 1>'s face. From the opening frame on, her lips move in perfect syllable-by-syllable sync with the singing in <Audio 1>, every mouth shape matching the song for the entire clip from 00:00.000 to the end, with no drift and no gap. She keeps singing along with the music, moving her lips to every word, continuing seamlessly from where <Video 1> stopped. Her expression remains a beautiful, restrained melancholy: soft longing eyes, slightly parted lips, a wistful gentle sadness; her brows stay relaxed, her gaze occasionally drifts down and back up. Her head tilts slowly and her shoulders and upper body sway subtly with the music rhythm, flowing continuously without any new start. Her hairpin tassels and sheer sleeves drift slightly with the movement. The same warm amber lantern light and cool teal shadow shape her face, the same faint smoke drifting behind her in the dark atmospheric backdrop. Only <Subject 1> appears, no text, no logos, no other people. overall_soundscape: Soft fabric rustle as the sleeves sway; gentle breathing between sung phrases; a faint low ambience of an old room with dust in lantern light. non_diegetic_music: N/A (the song is the diegetic reference audio she sings along to).