Sherry

Video

Image to video

AI Image to Video with Choathella by Sherry

Reference image

Quality

UltraS

Resolution

FHD

Duration

15 s

Native audio

On

Description

People limit: The video must contain no more than two people in every shot. The only people allowed are the two podcast hosts. Do not add guests, audience members, crew, background people, reflections of other people, posters with faces, or silhouettes.Create one single ultra clear 16:9 wide storyboard image arranged as a clean 4x4 grid, exactly 16 panels, for a 15-second realistic English podcast video with varied camera angles and dynamic camera movement. The same two white English-speaking podcast hosts appear consistently across all panels in a cozy modern podcast studio, filmed like real iPhone 15 Pro horizontal footage. Thin clean borders between panels, no text, no numbers, no watermark.STRICT PEOPLE LIMIT:Every panel must show no more than two people total. The only people allowed are the two podcast hosts. Do not show guests, audience members, crew, reflections of other people, background people, silhouettes, posters with people, photos of people, or anyone else. Some panels may show both hosts, and some close-up panels may show only one host, but never more than two people in any panel.Setting in every panel: wooden podcast table, professional black microphones on boom arms, headphones, open laptop, coffee cups, paper notes, warm desk lamp, acoustic foam panels, bookshelf, green plant, soft background practical lights, warm realistic indoor lighting, candid phone-camera look. Background must not contain any people, faces, portraits, human photos, or silhouettes.Characters must stay consistent:Left host: white young woman, late 20s, shoulder-length blonde hair with soft waves, cream knit sweater, small gold hoop earrings, natural makeup, realistic skin texture, friendly confident personality.Right host: white young man, early 30s, short brown hair, light stubble, navy casual overshirt over a white T-shirt, friendly focused expression, thoughtful conversational personality.Panel 1: wide establishing shot from table height, exactly two hosts visible, microphones and cozy studio background.Panel 2: slightly wider room angle from corner of studio, exactly two hosts at the table, bookshelf and lamp visible, no other people.Panel 3: slow push-in angle toward the woman speaking into the microphone, the man softly blurred in background listening.Panel 4: over-the-shoulder shot from behind the woman toward the man as he responds, microphone foreground blur, only these two hosts.Panel 5: close-up of the man speaking, natural English mouth shape, warm side light, no other people.Panel 6: reverse over-the-shoulder from behind the man toward the woman as she reacts and nods, only these two hosts.Panel 7: close-up of the woman reacting with a thoughtful smile, slight head tilt, warm lamp bokeh behind her, no other people.Panel 8: tabletop sliding shot across coffee cups, notes, laptop, and microphones, the two hosts softly blurred in background, no extra people.Panel 9: macro close-up of black podcast microphone and pop filter, no people visible or only the two hosts softly blurred, no extra faces.Panel 10: close-up of hands and gestures near microphone and paper notes, only the hosts’ hands visible, no extra people.Panel 11: side profile two-shot, exactly two hosts leaning toward microphones.Panel 12: low table-level angle between microphones, exactly two hosts facing each other.Panel 13: medium two-shot with exactly two hosts laughing naturally.Panel 14: close-up of the man listening and smiling, only him visible.Panel 15: close-up of the woman speaking directly toward the microphone, only her visible.Panel 16: final gentle pull-back wide shot, exactly two hosts smiling toward the camera, no other people.Visual style: ultra realistic iPhone 15 Pro footage stills, natural human skin texture, subtle pores, believable eyes, real facial micro-expressions, no beauty filter, no plastic skin, no frozen expressions, natural English mouth shapes while speaking, realistic warm shadows, slight phone lens distortion, high clarity.Negative constraints: more than two people, extra person, guest, audience, crew member, background person, human silhouette, portrait photo, poster with faces, reflected people, crowd, text, logo, watermark, anime, cartoon, CGI look, distorted faces, changing outfits, inconsistent characters.