Tiny Desk AI Prompt (Copy-Ready): Every Shot, Every Role

subject_definitions:
Subject 1 is the person in @Image 1 (a person, or a cartoon or game character, or a pet when @Image 1 shows one): [one sentence describing the person or character in photo 3: age range, hair, build] [what the person in photo 3 wears, piece by piece] Subject 1 keeps exactly this face, hair, skin tone, build and this outfit, piece by piece, in every shot. If @Image 1 shows only part of the body, the rest of the outfit continues naturally from what it shows. Subject 1 is the band's keyboard player, seated at the front in the middle playing the red stage keyboard.
Subject 2 is the person in @Image 2 (a person, or a cartoon or game character, or a pet when @Image 2 shows one): [one sentence describing the person or character in photo 4: age range, hair, build] [what the person in photo 4 wears, piece by piece] Subject 2 keeps exactly this face, hair, skin tone, build and outfit in every shot where they appear.
Subject 3 is the person in @Image 3 (a person, or a cartoon or game character, or a pet when @Image 3 shows one): [one sentence describing the person or character in photo 5: age range, hair, build] [what the person in photo 5 wears, piece by piece] Subject 3 keeps exactly this face, hair, skin tone, build and outfit in every shot where they appear.
The band has fixed places and never swaps them: Subject 1 sits at the front in the middle behind the red stage keyboard; Subject 2 stands behind Subject 1 on the left of the frame singing backup, both hands free, holding no instrument; Subject 3 stands behind Subject 1 on the right of the frame singing backup with a small green tambourine.
Each of Subject 1, Subject 2 and Subject 3 has a face of their own; no face appears on two band members, and nobody but Subject 1 has Subject 1's face.
If @Image 1 shows a video-game, cartoon or anime character, the whole video is rendered in that same style: any invented band member is a character of the same kind, and the room is rendered to match. If @Image 1 is a real photo, the whole video is photoreal. If @Image 1 shows a pet, Subject 1 stays that real animal, sitting up at the keyboard in the lead's place with its paws on the keys.
Subject 4 is the set: an intimate office concert filmed in daylight, the band squeezed in behind a desk in a cramped work corner: on the desk at the front a red stage keyboard; slim black microphone stands with small pencil microphones; behind the band tall wooden bookshelves packed floor to ceiling with vinyl records, books, plush toys, caps, figurines, bottles, mugs and colourful boxes; warm, soft, even office light, no stage lights, no audience in frame. No sign, poster, label or sticker is readable.
@Video 1 is a motion reference only: copy its shots, its cuts and their timing, its camera angles, lenses and camera moves, and every pose, gesture, head turn, mouth movement and hand on the instruments at the same moment. @Video 1 is already framed vertically in 9:16: copy its framing shot by shot, how large each person is in the frame and where the frame edges cut them. Take no person, face, hair, body, clothing, jewellery, glasses or headphones from @Video 1; none of its people appear.

summary:
[reference generation] A 6-second shot of an intimate office concert in Subject 4, following @Video 1: Subject 1 plays the red stage keyboard at the front, with Subject 2 and Subject 3 singing backup behind on the left and on the right.

retention_analysis:
Subject 1 (appears in [Shot 1]): fully_preserved - face, hair, skin tone, body and outfit from @Image 1.
Subject 2 (appears in [Shot 1]): fully_preserved - face, hair, skin tone, body and outfit from @Image 2.
Subject 3 (appears in [Shot 1]): fully_preserved - face, hair, skin tone, body and outfit from @Image 3.
Subject 4 (all shots): weak_reference - built from the text only; layout and camera from @Video 1.

detailed_description:
Vertical 9:16 frame. Natural documentary concert look, warm colour, sharp focus on the faces, soft background, one continuous shot following @Video 1, no cut.
[Shot 1] 0-6 s: medium shot at seated head height, camera locked off; Subject 1 sits at the front in the middle, seen from the chest up, head bowed over the red stage keyboard, both hands on the keys, nodding to the beat; Subject 2 stands behind on the left, half cut by the left frame edge, singing backup with both hands free, holding no instrument; Subject 3 stands behind on the right, from the waist up, singing backup and shaking a small green tambourine at shoulder height. Heads near the top of the frame against the shelves.

overall_soundscape:
A small room: soft keyboard clicks, breath on the saxophone, a little laughter between lines.

non_diegetic_music:
A warm live early-1980s funk-R&B groove at about 98 beats per minute, a male lead vocal with backing vocals, keyboard and a saxophone line; every gesture and cut lands on the beat.

Reference handling: @Image 1 sets Subject 1's identity, @Image 2 Subject 2's and @Image 3 Subject 3's: face, hair, skin tone, age, build and outfit; ignore each photo's background, pose and framing. @Video 1 sets only the shots, cuts, camera and performance.

Final rules override conflicting customization: Subject 1 is recognizable as the one in @Image 1, Subject 2 as the one in @Image 2 and Subject 3 as the one in @Image 3 in every shot where they appear, each in their own outfit from their photo throughout; nobody from @Video 1 appears; no blue knit beanie, no gold aviator sunglasses, no gold chain with a square pendant, no green, gold and blue patterned bomber jacket, no black knit beanie, no silver chain with a cross pendant, no blue wristband, no shaved head, no glasses, no black hoodie, unless a photo shows them; exactly three people in the shot, no one added; every band member keeps their place; Subject 2 holds no instrument and nothing at the mouth; keep it physically coherent; no captions, subtitles, watermarks, logos or brand names on screen or on anyone's clothes unless a photo shows them; no readable writing anywhere in the room.

subject_definitions:
Subject 1 is the person in @Image 1 (a person, or a cartoon or game character, or a pet when @Image 1 shows one): [one sentence describing the person or character in photo 1: age range, hair, build] [what the person in photo 1 wears, piece by piece] Subject 1 keeps exactly this face, hair, skin tone, build and this outfit, piece by piece, in every shot. If @Image 1 shows only part of the body, the rest of the outfit continues naturally from what it shows. Subject 1 is the band's lead singer, singing alone in close-up.
If @Image 1 shows a video-game, cartoon or anime character, the whole video is rendered in that same style: any invented band member is a character of the same kind, and the room is rendered to match. If @Image 1 is a real photo, the whole video is photoreal. If @Image 1 shows a pet, Subject 1 stays that real animal, singing to the lens in the close-up.
Subject 2 is the set: an intimate office concert filmed in daylight, the band squeezed in behind a desk in a cramped work corner: on the desk at the front a red stage keyboard; slim black microphone stands with small pencil microphones; behind the band tall wooden bookshelves packed floor to ceiling with vinyl records, books, plush toys, caps, figurines, bottles, mugs and colourful boxes; warm, soft, even office light, no stage lights, no audience in frame. No sign, poster, label or sticker is readable.
@Video 1 is a motion reference only: copy its shots, its cuts and their timing, its camera angles, lenses and camera moves, and every pose, gesture, head turn, mouth movement and hand on the instruments at the same moment. @Video 1 is already framed vertically in 9:16: copy its framing shot by shot, how large each person is in the frame and where the frame edges cut them. Take no person, face, hair, body, clothing, jewellery, glasses or headphones from @Video 1; none of its people appear.

summary:
[reference generation] A 7-second close-up from an intimate office concert in Subject 2, following @Video 1: Subject 1 sings alone to the lens.

retention_analysis:
Subject 1 (appears in [Shot 1]): fully_preserved - face, hair, skin tone, body and outfit from @Image 1.
Subject 2 (all shots): weak_reference - built from the text only; layout and camera from @Video 1.

detailed_description:
Vertical 9:16 frame. Natural documentary concert look, warm colour, sharp focus on the faces, soft background, one continuous shot following @Video 1, no cut.
[Shot 1] 0-7 s: close-up of Subject 1 alone, head and shoulders filling the frame, camera close at eye level, slowly pushing in, the shelves blurred behind; Subject 1 throws the head back laughing, sings with a huge grin looking toward the left of the frame, then turns to look straight into the camera lens with both eyes while still singing, keeps singing to the lens, and at the end lifts one hand beside the face. No other face in frame.

overall_soundscape:
A small room: soft keyboard clicks, breath on the saxophone, a little laughter between lines.

non_diegetic_music:
A warm live early-1980s funk-R&B groove at about 98 beats per minute, a male lead vocal with backing vocals, keyboard and a saxophone line; every gesture and cut lands on the beat.

Reference handling: @Image 1 sets Subject 1's identity: face, hair, skin tone, age, build and outfit; ignore its background, pose and framing. @Video 1 sets only the shots, cuts, camera and performance.

Final rules override conflicting customization: Subject 1 is recognizable as the one in @Image 1 in every shot where they appear and wears their own outfit from @Image 1 throughout; nobody from @Video 1 appears; no blue knit beanie, no gold aviator sunglasses, no gold chain with a square pendant, no green, gold and blue patterned bomber jacket, no black knit beanie, no silver chain with a cross pendant, no blue wristband, no shaved head, no glasses, no black hoodie, unless a photo shows them; no other face in the shot, no one added; keep it physically coherent; no captions, subtitles, watermarks, logos or brand names on screen or on anyone's clothes unless a photo shows them; no readable writing anywhere in the room.

subject_definitions:
Subject 1 is the person in @Image 1 (a person, or a cartoon or game character, or a pet when @Image 1 shows one): [one sentence describing the person or character in photo 2: age range, hair, build] [what the person in photo 2 wears, piece by piece] Subject 1 keeps exactly this face, hair, skin tone, build and this outfit, piece by piece, in every shot. If @Image 1 shows only part of the body, the rest of the outfit continues naturally from what it shows. Subject 1 is the band's saxophonist, playing a gold alto saxophone solo. Subject 1's face is exactly the face in @Image 1.
If @Image 1 shows a video-game, cartoon or anime character, the whole video is rendered in that same style: any invented band member is a character of the same kind, and the room is rendered to match. If @Image 1 is a real photo, the whole video is photoreal. If @Image 1 shows a pet, Subject 1 stays that real animal, sitting up with the gold alto saxophone at its mouth and its paws on the keys.
Subject 2 is the set: an intimate office concert filmed in daylight, the band squeezed in behind a desk in a cramped work corner: on the desk at the front a red stage keyboard; slim black microphone stands with small pencil microphones; behind the band tall wooden bookshelves packed floor to ceiling with vinyl records, books, plush toys, caps, figurines, bottles, mugs and colourful boxes; warm, soft, even office light, no stage lights, no audience in frame. No sign, poster, label or sticker is readable.
@Video 1 is a motion reference only: copy its shots, its cuts and their timing, its camera angles, lenses and camera moves, and every pose, gesture, head turn, mouth movement and hand on the instruments at the same moment. @Video 1 is already framed vertically in 9:16: copy its framing shot by shot, how large each person is in the frame and where the frame edges cut them. Take no person, face, hair, body, clothing, jewellery or headphones from @Video 1; none of its people appear.

summary:
[reference generation] A 4-second shot from an intimate office concert in Subject 2, following @Video 1: Subject 1 plays a saxophone solo.

retention_analysis:
Subject 1 (appears in [Shot 1]): fully_preserved - face, hair, skin tone, body and outfit from @Image 1.
Subject 2 (all shots): weak_reference - built from the text only; layout and camera from @Video 1.

detailed_description:
Vertical 9:16 frame. Natural documentary concert look, warm colour, sharp focus on the faces, soft background, one continuous shot following @Video 1, no cut.
[Shot 1] 0-4 s: medium close-up of Subject 1 alone in three-quarter profile facing the left of the frame, camera at shoulder height on Subject 1's left-front, locked off; Subject 1 plays the gold alto saxophone into a microphone on a long boom arm that crosses the frame diagonally, fingers moving on the keys, eyes down on the instrument; in the lower right corner the out-of-focus top of another band member's head, no face. The shelves behind.

overall_soundscape:
A small room: soft keyboard clicks, breath on the saxophone, a little laughter between lines.

non_diegetic_music:
A warm live early-1980s funk-R&B groove at about 98 beats per minute, a male lead vocal with backing vocals, keyboard and a saxophone line; every gesture and cut lands on the beat.

Reference handling: @Image 1 sets Subject 1's identity: face, hair, skin tone, age, build and outfit; ignore its background, pose and framing. @Video 1 sets only the shots, cuts, camera and performance.

Final rules override conflicting customization: Subject 1 is recognizable as the one in @Image 1 in every shot where they appear and wears their own outfit from @Image 1 throughout; nobody from @Video 1 appears; no blue knit beanie, no gold chain with a square pendant, no green, gold and blue patterned bomber jacket, no black knit beanie, no silver chain with a cross pendant, no blue wristband, no shaved head, no black hoodie, unless a photo shows them; no other face in the shot, no one added; keep it physically coherent; no captions, subtitles, watermarks, logos or brand names on screen or on anyone's clothes unless a photo shows them; no readable writing anywhere in the room.

subject_definitions:
Subject 1 is the person in @Image 1 (a person, or a cartoon or game character, or a pet when @Image 1 shows one): [one sentence describing the person or character in photo 3: age range, hair, build] [what the person in photo 3 wears, piece by piece] Subject 1 keeps exactly this face, hair, skin tone, build and this outfit, piece by piece, in every shot. If @Image 1 shows only part of the body, the rest of the outfit continues naturally from what it shows. Subject 1 is the band's keyboard player, seated at the front in the middle playing the red stage keyboard.
Subject 2 is the person in @Image 2 (a person, or a cartoon or game character, or a pet when @Image 2 shows one): [one sentence describing the person or character in photo 4: age range, hair, build] [what the person in photo 4 wears, piece by piece] Subject 2 keeps exactly this face, hair, skin tone, build and outfit in every shot where they appear.
Subject 3 is the person in @Image 3 (a person, or a cartoon or game character, or a pet when @Image 3 shows one): [one sentence describing the person or character in photo 5: age range, hair, build] [what the person in photo 5 wears, piece by piece] Subject 3 keeps exactly this face, hair, skin tone, build and outfit in every shot where they appear.
The band has fixed places and never swaps them: Subject 1 sits at the front in the middle behind the red stage keyboard; Subject 2 stands behind Subject 1 on the left of the frame singing backup, both hands free, holding no instrument; Subject 3 stands behind Subject 1 on the right of the frame singing backup with a small green tambourine.
Each of Subject 1, Subject 2 and Subject 3 has a face of their own; no face appears on two band members, and nobody but Subject 1 has Subject 1's face.
If @Image 1 shows a video-game, cartoon or anime character, the whole video is rendered in that same style: any invented band member is a character of the same kind, and the room is rendered to match. If @Image 1 is a real photo, the whole video is photoreal. If @Image 1 shows a pet, Subject 1 stays that real animal, sitting up at the keyboard in the lead's place with its paws on the keys.
Subject 4 is the set: an intimate office concert filmed in daylight, the band squeezed in behind a desk in a cramped work corner: on the desk at the front a red stage keyboard; slim black microphone stands with small pencil microphones; behind the band tall wooden bookshelves packed floor to ceiling with vinyl records, books, plush toys, caps, figurines, bottles, mugs and colourful boxes; warm, soft, even office light, no stage lights, no audience in frame. No sign, poster, label or sticker is readable.
@Video 1 is a motion reference only: copy its shots, its cuts and their timing, its camera angles, lenses and camera moves, and every pose, gesture, head turn, mouth movement and hand on the instruments at the same moment. @Video 1 is already framed vertically in 9:16: copy its framing shot by shot, how large each person is in the frame and where the frame edges cut them. Take no person, face, hair, body, clothing, jewellery, glasses or headphones from @Video 1; none of its people appear.

summary:
[reference generation] A 5-second shot of an intimate office concert in Subject 4, following @Video 1: Subject 1 plays the red stage keyboard at the front, with Subject 2 and Subject 3 singing backup behind on the left and on the right.

retention_analysis:
Subject 1 (appears in [Shot 1]): fully_preserved - face, hair, skin tone, body and outfit from @Image 1.
Subject 2 (appears in [Shot 1]): fully_preserved - face, hair, skin tone, body and outfit from @Image 2.
Subject 3 (appears in [Shot 1]): fully_preserved - face, hair, skin tone, body and outfit from @Image 3.
Subject 4 (all shots): weak_reference - built from the text only; layout and camera from @Video 1.

detailed_description:
Vertical 9:16 frame. Natural documentary concert look, warm colour, sharp focus on the faces, soft background, one continuous shot following @Video 1, no cut.
[Shot 1] 0-5 s: the same medium shot at seated head height, camera locked off; Subject 1 sits at the front in the middle, head down over the red stage keyboard, playing with both hands; Subject 2 stands behind on the left, half cut by the left frame edge, singing backup toward a microphone with both hands free, holding no instrument and nothing at the mouth; Subject 3 stands behind on the right, from the waist up, singing backup with a small green tambourine. Heads near the top of the frame against the shelves.

overall_soundscape:
A small room: soft keyboard clicks, breath on the saxophone, a little laughter between lines.

non_diegetic_music:
A warm live early-1980s funk-R&B groove at about 98 beats per minute, a male lead vocal with backing vocals, keyboard and a saxophone line; every gesture and cut lands on the beat.

Reference handling: @Image 1 sets Subject 1's identity, @Image 2 Subject 2's and @Image 3 Subject 3's: face, hair, skin tone, age, build and outfit; ignore each photo's background, pose and framing. @Video 1 sets only the shots, cuts, camera and performance.

Final rules override conflicting customization: Subject 1 is recognizable as the one in @Image 1, Subject 2 as the one in @Image 2 and Subject 3 as the one in @Image 3 in every shot where they appear, each in their own outfit from their photo throughout; nobody from @Video 1 appears; no blue knit beanie, no gold aviator sunglasses, no gold chain with a square pendant, no green, gold and blue patterned bomber jacket, no black knit beanie, no silver chain with a cross pendant, no blue wristband, no shaved head, no glasses, no black hoodie, unless a photo shows them; exactly three people in the shot, no one added; every band member keeps their place; Subject 2 holds no instrument and nothing at the mouth; keep it physically coherent; no captions, subtitles, watermarks, logos or brand names on screen or on anyone's clothes unless a photo shows them; no readable writing anywhere in the room.