Kyoto Morning Selfie Vlog
FORMAT: A single continuous vertical 9:16 video, maximum 15 seconds, filmed like a casual iPhone front-facing camera or DJI Osmo Pocket vlog. The result must feel like a real person spontaneously recording her morning—not an advertisement, cinematic travel montage, fashion shoot, or influencer campaign.
CHARACTER — MAYA: Maya is a 25-year-old East Asian woman with a natural, approachable appearance. She has a softly oval face, warm light-medium skin with neutral golden undertones, dark-brown almond-shaped eyes, naturally straight brows, a small rounded nose, and natural pink lips. Her face has believable human detail: visible pores, faint under-eye texture, subtle cheek redness, tiny skin imperfections, slight facial asymmetry, and natural smile lines. Do not smooth or perfect her skin.
Her long, naturally dark-brown hair is tied in a loose, slightly messy low ponytail. A few uneven strands and flyaway hairs frame her face and move naturally as she walks. Her hair must not appear salon-styled, glossy, or perfectly arranged.
She wears minimal everyday makeup: light concealer, softly brushed brows, a tiny amount of mascara, and clear lip balm. No glamorous makeup, false lashes, heavy contouring, glossy editorial skin, or beauty filter.
Her outfit is practical and slightly rumpled from travel: an oversized cream cotton hoodie with soft folds, black biker shorts, lightly worn white sneakers, and a small taupe crossbody bag resting naturally against her hip. No visible brand names or logos. She wears tiny silver stud earrings and has short, unpolished natural nails.
Maya is attractive but not posed like a professional model. Her posture is relaxed and slightly sleepy. She occasionally squints in the morning sunlight, brushes a loose strand of hair aside, glances at the street instead of constantly watching the lens, and briefly checks whether she is framed correctly. Her expressions are small and spontaneous rather than exaggerated. She speaks in a relaxed conversational voice with natural pauses and slight breathiness from walking.
IDENTITY CONSISTENCY: Maya’s face, hairstyle, outfit, body proportions, accessories, and skin tone must remain completely consistent throughout the clip. No facial morphing, changing clothes, beauty-filter effects, or sudden changes in age or ethnicity.
CAMERA: The clip begins immediately in vertical selfie mode, with Maya holding the camera naturally at arm’s length while stepping out of her guesthouse. Frame her from approximately mid-chest upward. The camera sits slightly below eye level rather than at a perfect professional angle.
Use believable smartphone stabilization with gentle walking bounce, small wrist movements, drifting headroom, minor horizon tilt, brief autofocus adjustment, and natural exposure changes as she steps from shade into sunlight. Occasionally crop a small part of her hair or shoulder. Her hand and recording device remain outside the frame. No selfie stick is visible.
The lens should behave like a real wide-angle smartphone selfie lens: mild edge distortion, deep focus, slightly compressed highlights, realistic detail, and modest front-camera dynamic range. Avoid shallow cinematic depth of field, artificial bokeh, crane shots, drone shots, perfect gimbal movement, dramatic zooms, slow motion, or impossible camera movement.
LIGHTING AND IMAGE: Natural morning sunlight only. The light is warm but not heavily color-graded. When Maya steps outside, the phone briefly adjusts its exposure before settling. Her skin retains pores and natural texture. Highlights on her forehead and nose are subtle and realistic. Shadows beneath her chin and around the eyes remain visible.
The footage should have modern smartphone clarity, realistic motion blur, restrained sharpening, natural colors, and mild highlight bloom. No film grain, VHS artifacts, retro filters, orange-and-teal grading, plastic skin, artificial face enhancement, or commercial polish.
SETTING: A quiet historic residential lane in Kyoto during the early morning. Maya exits a small traditional guesthouse with dark timber framing, pale plaster walls, a simple wooden sliding entrance, and a dark fabric noren curtain. The doorway connects physically and continuously to the street.
Outside is a narrow stone-paved lane lined with traditional wooden machiya townhouses, small potted plants, bicycles parked beside walls, subtle Japanese signage, overhead utility wires, and a tiny neighborhood bakery farther down the street. Soft sunlight passes between the buildings and creates irregular patches of light on the pavement.
The neighborhood feels inhabited rather than staged. One distant resident quietly cycles through the background without acknowledging the camera. A shopkeeper is barely visible preparing the bakery. No crowds, tour groups, landmarks, cherry-blossom spectacle, artificial fog, or perfectly empty theme-park atmosphere.
AMBIENT AUDIO: Realistic location sound recorded through a smartphone microphone: the guesthouse door sliding shut, Maya’s footsteps on stone, light fabric movement, distant bicycle tires, faint birds, a soft breeze, and subtle neighborhood activity. Her voice is clear but still belongs naturally within the environment. No background music, voice-over, dramatic sound design, or studio-clean audio.
PERFORMANCE AND TIMELINE:
0–4 SECONDS: Begin already recording. Maya steps through the guesthouse doorway in selfie mode and pulls the door closed behind her. The phone briefly adjusts from the darker interior to the bright street. Her framing is slightly low and imperfect. She starts walking and smiles gently at the lens.
MAYA: “Morning. I have no plan today.”
She gives a tiny amused exhale after speaking—not a performed laugh.
4–9 SECONDS: Without a cut, Maya turns her wrist to show the lane ahead. The movement is quick and slightly clumsy, briefly tilting the horizon. The camera reveals the wooden townhouses, stone pavement, parked bicycle, and morning sunlight. She pauses for a fraction of a second before turning the camera back toward herself. Autofocus takes a moment to return to her face.
MAYA: “Look how quiet it is.”
She glances past the lens toward the street while speaking.
9–13 SECONDS: Maya notices the small bakery ahead. She turns her head first, then subtly redirects the camera toward it while continuing to walk. A loose strand of hair falls across her cheek, and she casually brushes it away. Her smile grows naturally when she notices the bakery.
MAYA: “Oh—okay. Breakfast first.”
The “oh” should sound spontaneous, as though she genuinely just noticed it.
13–15 SECONDS: She turns the camera fully back toward her face and walks toward the bakery. Her face is slightly off-center, and the movement causes a small bounce in the frame. She gives the lens a quick, understated smile.
MAYA: “Let’s go.”
End abruptly while she is still walking, like a genuine social-media vlog clip rather than a composed ending.
REALISM REQUIREMENTS: Preserve natural human blinking, breathing, weight shifts, walking rhythm, hair movement, cloth physics, lip synchronization, background continuity, and spatial consistency. Maya must interact with the actual environment rather than appearing composited over it. Keep all gestures understated and unscripted. Avoid exaggerated smiling, constant eye contact, presenter gestures, fashion posing, flawless framing, empty frozen backgrounds, warped architecture, unreadable prominent signage, extra fingers, facial distortion, or uncanny movement.
![Cinematic Bungee Jump Action Video — Reference image: [MAIN CHARACTER IMAGE user provided]
[0:00–0:03] Platform — Confidence Build
Main…](https://pbs.twimg.com/amplify_video_thumb/2074439617424887808/img/rZkp9OmieE1Wkq0Y.jpg)
![Nature Reclaiming Cities Cartographer Scene — [0-3s] Wren stands on a high ridge overlooking a vast changed landscape mountains where cities were, forests recla](https://pbs.twimg.com/amplify_video_thumb/2076583065087070208/img/Fv-CJ4Cjfrz_-v-C.jpg)
![Samurai Electric Sword Drawing — BGMなし、字幕なし。
背景は日本の寂れたお寺。
１）[添付画像]の戦闘スーツを着た人間が背中の日本刀を右手で抜く。
２）抜いた日本刀を横に構え、刀身の根元を左手の掌…](https://pbs.twimg.com/amplify_video_thumb/2081649441153728512/img/rad-a1B2er6jaDCl.jpg)
![King Kong Attack Video Prompt for Seedance 2.0 — [主体]: @图片1 中的巨型大猩猩, 黑色银背毛发根根分明, 肌肉轮廓极度写实, 双眼充满愤怒, 展现出电影级的五官细节1.
[动作]: 巨型动物@图片从深海中缓慢站起, 水流顺着强壮的肌肉缓慢滑…](https://pbs.twimg.com/amplify_video_thumb/2034426032493903872/img/ZJjKhYqSGkOxzACF.jpg)
