REFERENCES
@Image1 (IMG_CLIP_34.jpg) = START FRAME and character reference. The video begins exactly on this frame: a mirror selfie of the same woman holding a white iPhone in her right hand, left hand resting in her hair, dark grey fleece bathrobe, loose wavy light-brown hair with lighter highlights, light green-grey eyes, freckles, soft pink-beige nails, white bedding visible in the mirror behind her. No end frame: the clip ends wherever the action naturally lands.

CHARACTER LOCK
The same woman as @Image1 throughout. Identity must not drift: no face morphing, no change of eye color, hair, nails or clothing. The white phone in her right hand keeps its shape (white case, dual camera, Apple logo), no melting or warping.

VOICE
American English, female, mid-20s, slightly low, steady and serious. Direct, no smile in the voice, a little challenging, like a final warning said calmly. Brisk pace, no filler. Not a whisper, not a scream, not a commercial voice. Close-mic phone quality with slight room tone. Lips sync exactly to the words.

SETTING
Her bedroom, mirror selfie, soft indoor light, neutral grey-beige walls, curtain on the left edge, white bedding behind her. No other people.

FORMAT
Duration 4 seconds. Aspect ratio 4:3 (1440x1080). One continuous shot, no cuts. Natural motion, 24 fps.

SHOT BREAKDOWN
Same framing as @Image1. She is serious throughout, never smiling.

0.0-0.2 s: Hard direct stare, jaw set. The hand in her hair starts dropping as she starts speaking almost immediately.

0.2-1.0 s: She says, low and direct: "Now you decide:" Stress on "decide". Brows slightly lowered.

1.0-1.2 s: Minimal beat of silence. A slight tilt of the head to the right, eyes stay fixed.

1.2-1.8 s: She says, dry and almost dismissive: "Keep scrolling," with one eyebrow lifting a touch and a tiny shrug of the shoulders.

1.8-2.0 s: Minimal beat. Stillness, steady stare.

2.0-3.6 s: She says, more intense and slightly faster: "or learn this before it's too late." Stress on "learn" and on "late". She leans slightly toward the mirror and the camera pushes in on her eyes (framing tightens about 10%).

3.6-4.0 s: She stops talking, holds a serious stare into the mirror/lens, lips closed, jaw set, one short exhale. No smile.

CAMERA
Handheld, the iPhone in her right hand is the camera: natural arm sway and breathing movement, slow push-in across the whole clip, slightly stronger push-in at 2.0-3.6 s. About 24mm equivalent look. Face and phone sharp, background soft. No whip pans, no cuts.

LIGHT AND LOOK
Soft indoor ambient light, slightly cool neutral tones, realistic and stable catchlights in both eyes. Authentic iPhone video look: mild sensor noise, slight softness at the edges, natural dynamic range, no HDR halos.

AUDIO
Her voice is the main sound, close and clear. Very soft room tone, tiny fabric rustle. No music, no sound effects, no voiceover.

GLOBAL REALISM
Visible pores, fine facial hair, natural freckles, real eye moisture, natural blinks every 2-4 seconds, subtle jaw and neck tension when delivering the last phrase. Fingers hold the phone naturally. Looks like a real mirror selfie video, not a rendered avatar.

NEGATIVE
No face morphing or identity drift, no changing hair, nails or robe, no plastic skin, no beauty filter, no smile, no exaggerated mouth movements, no lip-sync mismatch, no extra fingers, no warped or melting phone, no reflection glitches, no second person, no text, no subtitles, no watermark, no logos, no cuts, no cartoon look.