REFERENCE LIST: @Image1 — exact location reference: modern minimalist living room interior, beige sectional sofa, dark wood kitchen island in the background, warm ambient cove lighting along the ceiling perimeter, oak flooring, floor-to-ceiling windows with sheer curtains, round coffee tables, dining area visible behind. Use as the exact set/location for the scene — she is sitting on this sofa. @Image2 — strict identity reference for the main character's face (front, 3/4, and profile views): oval face, light green-blue eyes, freckles across cheeks and nose, dark brown wavy hair, natural fair skin. Use @Image2 as strict identity reference. Preserve exact likeness throughout. No beautification. No deformation. Stable face throughout. @Image3 — exact outfit and body reference: orange oversized turtleneck sweater, layered pearl necklaces draped over the sweater, beige wide-leg pleated trousers with a thin pearl belt detail, wavy shoulder-length brown hair, slim medium build. Use as strict clothing and body-type reference. @Audio1 — voice tone, timbre and pacing reference only. Match the warmth, honesty and natural conversational rhythm of the reference voice ("Fiona — chill, natural" style). Voice tone reference @Audio1, no lip sync — mouth movement generated independently, matching only the vocal character of @Audio1. FORMAT: 9:16 vertical VISUAL STYLE & COLOR PALETTE: Realistic handheld iPhone footage aesthetic, not cinematic color grade. Warm neutral tones — beige, oak wood, soft amber ambient light, muted orange from the sweater as accent color. Natural indoor color temperature, slightly warm white balance, no heavy stylization, no film grain overlay. 4K clarity but styled as authentic smartphone capture. LOCATION & ATMOSPHERE: Interior of a modern designer living room (@Image1), warm and lived-in, soft ambient light from cove lighting and pendant lamps, relaxed mid-afternoon mood, candid and slightly confiding atmosphere, as if letting the viewer in on a secret. SHOT BREAKDOWN: [0:00–3s] Medium shot, character (@Image2 face, @Image3 outfit) seated on the sectional sofa (@Image1), facing camera directly. Handheld iPhone framing, static camera position, no push-in, no zoom, minimal natural micro-shake only. She speaks in a relatable, slightly knowing tone, natural blinking, subtle head tilts, casual open expression. Voice tone and pacing follow the character of @Audio1. Line: "Look, we all know AI can make some great visuals at this point." [3:00–6s] Same medium shot, same fixed handheld framing, no camera movement. Her expression shifts into a more candid, confiding look, eyebrows lifting slightly as she reveals the catch, natural blinking continues, subtle hand gesture emphasizing the point, authentic micro-expressions. Voice tone and pacing follow the character of @Audio1. Line: "But what nobody tells you is you usually need to be incredibly skilled" [6:00–9s] Same medium shot, same fixed handheld framing, no camera movement. She continues with a slightly wry, knowing expression, natural blinking continues, authentic micro-expressions. Voice tone and pacing follow the character of @Audio1. Line: "to get the best out of it." [9:00–12s] Same medium shot, same fixed handheld framing, no camera movement. Her expression becomes more direct and pointed, a small nod for emphasis, natural blinking continues, authentic micro-expressions. Voice tone and pacing follow the character of @Audio1. Line: "You need to write the perfect prompt." AUDIO: Voice tone reference @Audio1, no lip sync required. Ambient room tone — natural echo of a real apartment interior, faint outdoor city hum through windows, no studio-clean audio, no added music, realistic room acoustics. TECHNICAL TAIL: Stable face throughout. No morphing. No deformation. No flickering. No ghosting. Realistic physics. 4K cinematic.
REFERENCE LIST: @Image1 — exact location reference: modern minimalist living room interior, beige sectional sofa, dark wood kitchen island in the background, warm ambient cove lighting along the ceiling perimeter, oak flooring, floor-to-ceiling windows with sheer curtains, round coffee tables, dining area visible behind. Use as the exact set/location for the scene — she is sitting on this sofa. @Image2 — strict identity reference for the main character's face (front, 3/4, and profile views): oval face, light green-blue eyes, freckles across cheeks and nose, dark brown wavy hair, natural fair skin. Use @Image2 as strict identity reference. Preserve exact likeness throughout. No beautification. No deformation. Stable face throughout. @Image3 — exact outfit and body reference: orange oversized turtleneck sweater, layered pearl necklaces draped over the sweater, beige wide-leg pleated trousers with a thin pearl belt detail, wavy shoulder-length brown hair, slim medium build. Use as strict clothing and body-type reference. @Audio1 — voice tone, timbre and pacing reference only. Match the warmth, honesty and natural conversational rhythm of the reference voice ("Fiona — chill, natural" style). Voice tone reference @Audio1, no lip sync — mouth movement generated independently, matching only the vocal character of @Audio1. FORMAT: 9:16 vertical VISUAL STYLE & COLOR PALETTE: Realistic handheld iPhone footage aesthetic, not cinematic color grade. Warm neutral tones — beige, oak wood, soft amber ambient light, muted orange from the sweater as accent color. Natural indoor color temperature, slightly warm white balance, no heavy stylization, no film grain overlay. 4K clarity but styled as authentic smartphone capture. LOCATION & ATMOSPHERE: Interior of a modern designer living room (@Image1), warm and lived-in, soft ambient light from cove lighting and pendant lamps, relaxed mid-afternoon mood, candid and slightly confiding atmosphere, as if letting the viewer in on a secret. SHOT BREAKDOWN: [0:00–3s] Medium shot, character (@Image2 face, @Image3 outfit) seated on the sectional sofa (@Image1), facing camera directly. Handheld iPhone framing, static camera position, no push-in, no zoom, minimal natural micro-shake only. She speaks in a relatable, slightly knowing tone, natural blinking, subtle head tilts, casual open expression. Voice tone and pacing follow the character of @Audio1. Line: "Look, we all know AI can make some great visuals at this point." [3:00–6s] Same medium shot, same fixed handheld framing, no camera movement. Her expression shifts into a more candid, confiding look, eyebrows lifting slightly as she reveals the catch, natural blinking continues, subtle hand gesture emphasizing the point, authentic micro-expressions. Voice tone and pacing follow the character of @Audio1. Line: "But what nobody tells you is you usually need to be incredibly skilled" [6:00–9s] Same medium shot, same fixed handheld framing, no camera movement. She continues with a slightly wry, knowing expression, natural blinking continues, authentic micro-expressions. Voice tone and pacing follow the character of @Audio1. Line: "to get the best out of it." [9:00–12s] Same medium shot, same fixed handheld framing, no camera movement. Her expression becomes more direct and pointed, a small nod for emphasis, natural blinking continues, authentic micro-expressions. Voice tone and pacing follow the character of @Audio1. Line: "You need to write the perfect prompt." AUDIO: Voice tone reference @Audio1, no lip sync required. Ambient room tone — natural echo of a real apartment interior, faint outdoor city hum through windows, no studio-clean audio, no added music, realistic room acoustics. TECHNICAL TAIL: Stable face throughout. No morphing. No deformation. No flickering. No ghosting. Realistic physics. 4K cinematic.
