O reel mostra-me a falar numa praia sobre kits DIY de turbinas para móveis, intercalado com B-roll de IA: uma poltrona levanta-se com quatro mini turbinas, e um amigo e eu voamos com o nosso sofá até à montra de uma loja para comprar snacks. As falas decorrem de 2.4 a 5.9 segundos, e cada clip tem uma frase para cobrir.

Todas as falhas de câmara abaixo resultaram dos meus prompts. Os modelos fizeram o que escrevi, por isso a parte útil é o que escrever em alternativa.

Uma câmara fixada ao sujeito

Para o voo de regresso da loja para casa, queria que ambos os rostos permanecessem grandes, por isso o prompt do MiniMax H3 foi: “A câmara voa para trás em frente ao sofá à mesma velocidade, mantendo o sofá centrado e com o mesmo tamanho no plano.”

O H3 fez exatamente isso. O sofá permanece no meio do plano durante todo o voo enquanto a cidade desliza por trás, assemelhando-se a uma passadeira. Uma snorricam, uma câmara montada no corpo do ator, obtém o mesmo efeito de fixação propositadamente, para transmitir pânico ou desorientação.

Numa viagem, o sujeito precisa de movimento no ecrã: entra, atravessa, diminui e sai. Dê à câmara uma velocidade relativa ao sujeito, mais lenta para que o sujeito se afaste, e conte o que passa: “três telhados e um pequeno varrimento de quadrado sob a lente”.

Um grande movimento num plano curto

Para uma versão horizontal do B-roll, eu queria uma câmara em movimento e escrevi movimentos que se adequassem a um plano de 20 segundos. O plano do futebol tinha de fazer um movimento de grua da vista central para cima para olhar para baixo sobre o sofá, e depois voltar com a grua, em 3.8 segundos. O prompt dizia “amplitude média a velocidade lenta”, mas esse percurso nesse tempo não pode ser lento.

MiniMax H3 Turbo · 4 s

Plano zenital em menos de dois segundos

Do nível dos olhos para diretamente acima do sofá em 1.8 segundos, e depois volta a descer através do limoeiro.

MiniMax H3 Turbo · 6 s

O mundo inclina-se e volta ao lugar

A cadeira levanta-se enquanto a câmara oscila acima dela e regressa, tudo em cerca de dois segundos e meio.

Um clipe tão curto mantém apenas um movimento de câmara, tal como um plano com slider num set. É isto em que estou a trabalhar agora:

Duração do planoO que encaixaComo escrever
3 a 4 sUm movimento a uma velocidade lenta constante, numa única direção“um lento push-in, cerca de 8% mais perto no final”
5 a 6 sUm movimento, com um lento ease-out se desejar um“um deslize lateral lento de meio metro”
8 s ou maisUma mudança de movimento pode funcionarA sequência abaixo, para uma viagem entre dois locais

Um pequeno movimento, com um número

Depois, fiz os mesmos planos em Google Flow como clips de 4 segundos, cada um com um movimento lento e um tamanho definido. Dois deles estão abaixo. Parecem calmos e a ação é clara, sendo estes os clips que foram incluídos no reel final.

Google Flow · 4 s

Botão, jatos, descolagem

A prensa, a ignição e o elevador são todos legíveis, porque a câmara não os altera.

Google Flow · 4 s

Turbinas, uma deriva suave

O escape continua a cair verticalmente e o fundo desloca-se um pouco.

O movimento de fluxo foi muito inferior aos números que lhe atribuí. Comparei o fundo no último fotograma de cada clip com o seu primeiro fotograma, uma verificação aproximada com uma precisão de cerca de 1%. As duas últimas linhas são os planos de futebol e de snacks vazios, que também foram incluídos no reel.

PlanoSolicitadoMedido pelo último fotograma
PoltronaCerca de 5% mais pertoSem aproximar; o enquadramento deslocou-se cerca de 4% da sua altura
TurbinasArco de 15 graus, cerca de 15% mais próximoSem aproximar; cerca de 2% da sua largura lateralmente
FutebolCerca de 8% mais pertoDe volta ao fotograma inicial, após um afastamento de cerca de 3% a meio do percurso
Snacks vaziosCerca de 8% mais pertoCerca de 3% mais largo, na direção oposta

Para B-roll sob uma voz que estava boa, e decidi mantê-los. Se precisar de um zoom in, as pessoas vão notar; peça ao Flow mais do que deseja e depois compare o primeiro e o último fotograma. O H3 foi no sentido oposto quando lhe dei espaço, por isso verifique cada modelo separadamente. Tenho apenas estas quatro tomadas de Flow, e não apliquei os mesmos valores ao H3.

Os fotogramas fixos têm prioridade sobre o prompt, por isso verifique se a câmara que descreve consegue ligá-los. O meu fotograma final aprovado da poltrona foi filmado de uma câmara mais alta, o que força um grande movimento por mais pequeno que peça, por isso escrevi apenas a poltrona Flow a partir do primeiro fotograma. Quando ambos os fotogramas partilham o mesmo enquadramento, o movimento não tem para onde ir. Cortar o último fotograma de forma ligeiramente mais apertada deve permitir um push-in para onde aterrar, mas não tenho nenhuma tomada que o prove.

Uma jornada entre dois locais

O voo da montra da loja até ao terraço de casa é o único plano que necessitou de uma câmara em mudança, porque o primeiro e o último fotogramas estão em locais diferentes. Funcionou como uma tomada contínua em quatro tempos:

  1. A câmara permanece junto à janela e o sofá voa para fora do plano no canto superior direito. Sustente um momento no céu vazio.
  2. A câmara se desloca sozinha, um voo FPV ou de drone sobre os telhados.
  3. A câmara chega primeiro ao terraço e estabiliza no tapete vazio.
  4. O sofá entra no plano pelo topo e abranda até ao último fotograma.

Sair do plano e voltar dá ao espectador a noção de distância, e os rostos só precisam de detalhe no primeiro e no último momento, onde os fotogramas fixos o fornecem.

MiniMax H3 Turbo · 5 s

Todos os quatro tempos em 5 segundos

A falha é a transição: por volta dos 4 segundos, o sofá aparece como um rasto e ambos os rostos deformam-se durante cerca de quatro fotogramas, por isso verifique esse momento fotograma a fotograma.

Google Flow · 8 s

A tomada que foi para o reel

Oito segundos deram espaço a cada tempo, e ainda assim tive de o cortar. A fala deixou 4.35 segundos, por isso removi o meio do voo e reproduzi o resto a cerca de 1.1x. Pedir oito segundos foi o meu erro de planeamento; um estafeta deve começar com base na duração da frase.

Como escrever a câmara

Dê à câmara a sua própria frase, com o movimento, o seu tamanho e a sua velocidade. Se misturada na frase do sujeito, o modelo pode dividir o movimento entre ambos. A ação deve ocorrer nos primeiros segundos, porque um clipe de 4 segundos pode ter apenas 2.5 segundos na montagem:

Camera: one slow, steady [push-in / arc / slide] for the whole shot, about [8% closer / 15 degrees / half a metre] by the end, constant slow speed, same height and angle.
Action, in the first three seconds: [what the subject does].

Descreva o que está no fotograma e evite usar “sem X”. O MiniMax H3 não tem um canal negativo e tende a mostrar o que nomeia, por isso escrevi “o tapete permanece plano no deck” em vez de “o tapete não se move”.

Mais movimentos, e a técnica

Para mais movimentos, aicameramovements.com tem 46 movimentos de câmara nomeados com pré-visualizações em loop e um prompt para copiar em cada um. Os seus prompts deixam o tamanho em aberto, por isso adicione o número por si mesmo.

Transformei estas regras numa competência que um agente de IA pode seguir ao escrever prompts de vídeo: ajustar o tamanho do movimento pela duração do plano, o relay de quatro tempos, o que fazer com fotogramas fixos e qual movimento se adequa a cada tempo. Descarregue o ficheiro e peça ao seu agente de IA para instalar esta competência.

Descarregar camera_moves_skill.md

MiniMax H3 completo · 5 s · primeiro e último fotograma

O voo bloqueado

How the reference pictures align with the target video - Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video; Picture 2 (from Shot 1) aligns with the 5.17-second mark of the target video.

integrated_multimodal_description: [Shot 1] Photoreal digital cinema, bright Portuguese afternoon sun from the upper left, crisp deep focus, a single continuous aerial take with no cuts. The scene opens exactly on <Picture 1>: a worn sage-green fabric sofa hovers in mid-air beside an open second-floor window with a teal shutter on a whitewashed Portuguese building, about four and a half metres above a narrow cobbled street; far below are the green awning and MERCEARIA sign of a small grocery and a street of white houses running down to a blue river. Four brushed-steel turbines under the sofa blow steady glowing exhaust columns straight down. On the left sits a slim young man with platinum-blond hair and a thin moustache and goatee, in an oatmeal hoodie, light-grey joggers and tan slippers, a blue bowl on his lap. On the right sits a man with short light-brown hair, clean-shaven, in a navy T-shirt, faded jeans and navy slippers, holding a tablet in his left hand with its dark-grey back toward the camera; with his right hand he takes a brown paper grocery bag holding crisp packets, a drink bottle and a baguette from a smiling dark-haired shopkeeper woman leaning out of the window. From 00:00.000 to 00:01.100 the shopkeeper releases the bag with a small wave and stays inside at the window; the man on the right lifts the bag across and stands it upright on the seat between the two men, the baguette sticking out of the top. From 00:01.100 to 00:03.500 the sofa rises a metre, turns gently away from the building and flies forward over the town, level and steady, both men seated and relaxed. Directly beneath it pass, clearly and in focus, terracotta tiled rooftops, white chimneys, a small square with a tree and glimpses of the blue river, all moving past at a steady readable pace. Meanwhile the blond man pulls a red crisp packet out of the bag and tears it open, and the man on the right rests his right hand on the small black button panel on the right-hand armrest, steering, the tablet still in his left hand with its back to the camera. The camera flies backward in front of the sofa at the same speed, with large amplitude at medium speed, keeping the sofa centred and the same size in frame, so both men's faces stay large, sharp and fully visible. From 00:03.500 to 00:04.600 the sofa slows and descends toward a terracotta-tiled terrace in front of a whitewashed house with teal shutters, cream French doors, a lemon tree and pots of lavender; the camera decelerates and lowers with it to terrace height as the house rises into the background, and the sofa comes to a steady hover about half a metre above a charcoal mat, exhaust still glowing straight down. The blond man starts pouring crisps from the red packet into the blue bowl. From 00:04.600 to 00:05.170 the composition holds exactly as in <Picture 2>: the sofa hovering over the mat, the grocery bag between the men, crisps pouring into the bowl, the tablet's back to the camera, his right hand on the armrest buttons, both men smiling.

overall_soundscape: The crinkle of a paper bag, a steady turbine whine, wind rushing past during the flight, distant town ambience, church bells far away and swifts, the tear of a crisp packet, then crisps rattling into a bowl as the whine settles into an even hover.

non_diegetic_music: N/A

MiniMax H3 Turbo · 6 s · primeiro e último fotograma

A grua da poltrona

How the reference pictures align with the target video - Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video; Picture 2 (from Shot 1) aligns with the 6.58-second mark of the target video.

integrated_multimodal_description: [Shot 1] Photoreal digital cinema, natural daylight, widescreen, a single continuous take with a moving camera. The scene opens exactly on <Picture 1>: a man with short light-brown hair, a dark-green sweatshirt, beige chinos and brown slippers sits in an olive-green fabric recliner with its footrest raised, reading an open paperback held in both hands, eyes open on the page, calm face. The recliner stands on a charcoal carpet on a weathered wooden garden deck in front of a red-brick house with white French doors, terracotta pots and a flowering garden on both sides. A thick black control pad with grey buttons and one green button sits on top of the armrest at the left of the chair. Under the seat four compact brushed-steel turbines point straight down, cold. From 00:00.000 to 00:02.300 the camera dollies slowly toward the chair with small amplitude while he reads, then takes his right hand off the book, keeping it open in his left, and presses the green button with his index finger. At 00:02.400 the four turbines ignite, glowing exhaust and heat shimmer blowing straight down onto the carpet. From 00:02.800 to 00:05.000 the recliner lifts off level to about half a metre above the carpet, which stays flat on the deck, and he smiles; the camera cranes up with medium amplitude at medium speed, rising above the chair and looking down on him and the glowing jets, the deck and carpet opening up below. From 00:05.000 to 00:06.000 the camera eases back down with small amplitude at slow speed to the chair's height. From 00:06.000 to 00:06.580 the composition holds exactly as in <Picture 2>: the chair hovering over the empty carpet, book in his left hand, right index finger on the green button, a pleased smile, eyes open.

overall_soundscape: Quiet garden ambience with birdsong and the rustle of a page, a click of the button, then four small turbines spooling up into a smooth steady whine with a soft rush of air onto the carpet.

non_diegetic_music: N/A

MiniMax H3 Turbo · 4 s · primeiro e último fotograma

O grua de futebol

How the reference pictures align with the target video - Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video; Picture 2 (from Shot 1) aligns with the 4.46-second mark of the target video.

integrated_multimodal_description: [Shot 1] Photoreal digital cinema, natural daylight, widescreen, a single continuous take with a moving camera. The scene opens exactly on <Picture 1>: two men sit side by side on a worn sage-green fabric sofa on a terracotta-tiled terrace in front of a whitewashed Portuguese house with teal shutters and cream French doors, a lemon tree, pots of lavender and a distant river view, under bright afternoon daylight. The sofa rests on a charcoal mat; the four brushed-steel turbines under it point down at the mat, cold and still. On the left sits a slim young man with platinum-blond hair and a thin moustache and goatee, in an oatmeal hoodie, light-grey joggers and tan slippers. On the right sits a man with short light-brown hair, clean-shaven, in a navy T-shirt, faded jeans and navy slippers. The blond man holds a blue bowl of crisps on his lap, his right hand in the bowl. The man on the right holds a tablet in both hands with its dark-grey back toward the camera and its screen toward the two of them; both watch a football match on it. From 00:00.000 to 00:01.800 the camera cranes up from the centre view with medium amplitude at slow speed, rising to look down over the sofa, the bowl and the terrace tiles. From 00:01.800 to 00:03.800 it cranes back down with medium amplitude at slow speed to the centre view. Meanwhile the blond man picks up one of the last crisps and raises it to his mouth, eyes on the tablet, and the man on the right breaks into a warm smile at the match, the tablet steady with its back to the camera. From 00:03.800 to 00:04.460 the composition holds as in <Picture 2>: the blond man biting the crisp over a nearly empty bowl, the man on the right smiling at the hidden screen.

overall_soundscape: A crisp crunch, faint football commentary and crowd noise from the tablet speaker, a light breeze and distant gulls.

non_diegetic_music: N/A

Google Flow · 4 s

A poltrona

Photorealistic, natural daylight, one continuous take. A man with short light-brown hair, a dark-green sweatshirt, beige chinos and brown slippers sits in an olive-green fabric recliner with its footrest raised, reading an open paperback held at chest height in both hands, eyes open, calm face. The recliner stands on a charcoal carpet on a weathered wooden garden deck in front of a red-brick house with white French doors, terracotta pots and a flowering garden. A thick black control pad with grey buttons and one green button sits on top of the armrest at the left of the chair. Under the seat four compact brushed-steel mini jet turbines point straight down, switched off.
Camera: one slow, steady push-in for the whole shot, about 5% closer by the end, constant slow speed, same height and angle.
Action: in the first second he takes his right hand off the book, keeping it open in his left hand, and presses the green button with his index finger. Right after the press the four turbines ignite, glowing exhaust and heat shimmer blowing straight down onto the carpet. Then the recliner lifts off vertically, slowly and perfectly level, rising about half a metre while the carpet stays flat on the deck; he settles back with a small pleased smile, eyes open, finger still on the button, and the chair hovers steadily on four glowing downward jets.
Sound: garden birdsong, a click of the button, then four small turbines spooling up into a smooth steady whine with a soft rush of air onto the carpet.

Google Flow · 4 s

As turbinas

Photorealistic macro product shot, natural garden daylight, shallow depth of field, one continuous take. A low view under an olive-green fabric recliner hovering just above a charcoal carpet on a wooden garden deck; the sitter's beige chinos and brown slippers at the top of the frame. Four compact brushed-steel mini jet turbines in a row under the seat point straight down, each blowing a warm glowing column of exhaust and heat shimmer onto the carpet; the garden, terracotta pots and brick house are soft behind. The chair stays perfectly still in the air.
Camera: one slow, steady move for the whole shot - a gentle arc of about 15 degrees to the right around the turbines while drifting about 15% closer, constant slow speed, so the row of turbines turns slightly in perspective and the blurred garden slides behind them.
The exhaust keeps falling straight down, rippling the carpet fibres and bending the light.
Sound: a close, steady turbine whine and a constant rush of air onto the carpet, faint birdsong.

MiniMax H3 Turbo · 5 s · primeiro e último fotograma

O estafeta em H3

How the reference pictures align with the target video - Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video; Picture 2 (from Shot 1) aligns with the 5.17-second mark of the target video.

integrated_multimodal_description: [Shot 1] Photoreal digital cinema, bright Portuguese afternoon sun, crisp deep focus, one continuous take in which the camera changes its move from beat to beat. The scene opens exactly on <Picture 1>: a worn sage-green fabric sofa hovers in mid-air beside an open second-floor window with a teal shutter on a whitewashed Portuguese building, about four and a half metres above a narrow cobbled street; far below are the green awning and MERCEARIA sign of a small grocery and a street of white houses running down to a blue river. Four brushed-steel turbines under the sofa blow glowing exhaust straight down. On the left sits a slim young man with platinum-blond hair and a thin moustache and goatee, in an oatmeal hoodie, light-grey joggers and tan slippers. On the right sits a man with short light-brown hair, clean-shaven, in a navy T-shirt, faded jeans and navy slippers. The blond man holds a blue bowl on his lap; the man on the right holds a tablet in his left hand with its dark-grey back toward the camera and with his right hand takes a brown paper grocery bag with crisp packets, a drink bottle and a baguette from a smiling dark-haired shopkeeper woman leaning out of the window. From 00:00.000 to 00:00.800 the camera stays still: the shopkeeper lets go of the bag and waves, and he sets the bag upright on the seat between the two men. From 00:00.800 to 00:01.700 the camera stays where it is while the sofa rises and accelerates away to the upper right, shrinking quickly, and flies out of the frame past its top-right edge; the camera tilts up with small amplitude at slow speed after it and holds for a moment on the empty blue sky above the rooftops and the shopkeeper still waving at the window. From 00:01.700 to 00:03.500 the camera itself takes off: an FPV camera flight in one continuous take, the viewer is the flying camera, fast and low with large amplitude, skimming over terracotta tiled rooftops, weaving between white chimneys, three rooftops and a small square with a tree sweeping under the lens, then diving along a sloping street toward the river. From 00:03.500 to 00:04.200 the camera arrives at a terracotta-tiled terrace in front of a whitewashed house with teal shutters, cream French doors, a lemon tree and pots of lavender, decelerates sharply and settles at terrace height into the end-frame composition, where a charcoal mat lies empty in the middle of the tiles and the warm afternoon light is still. From 00:04.200 to 00:04.700 the sofa drops into the frame from its top edge with both men seated, the four turbines blowing glowing exhaust straight down, slows and comes to a steady hover about half a metre above the mat, the grocery bag between the men; the blond man starts pouring crisps from a red packet into the blue bowl, and the man on the right holds the tablet with its back to the camera, his right hand on the armrest buttons. The camera holds still. From 00:04.700 to 00:05.170 the composition holds exactly as in <Picture 2>.

overall_soundscape: The crinkle of a paper bag and the shopkeeper's laugh, a turbine whine that rises and fades into the distance, wind roaring past during the camera's flight over the rooftops, swifts and distant church bells, then the whine growing again as the sofa drops in, and crisps rattling into a bowl as it settles into an even hover.

non_diegetic_music: N/A

Google Flow · 8 s

O estafeta no Flow

Photorealistic cinematic shot, bright Portuguese afternoon sun, one continuous 8-second take. A worn sage-green sofa on four brushed-steel mini jet turbines hovers in the air. On the left sits a slim young man with platinum-blond hair in an oatmeal hoodie and light-grey joggers, a blue bowl on his lap; on the right a man with short light-brown hair in a navy T-shirt and faded jeans, holding a tablet with its dark-grey back toward the camera.
0-1.5 s: beside an open second-floor window above a cobbled street and the MERCEARIA grocery, the man on the right takes a brown paper grocery bag with a baguette from the smiling shopkeeper and sets it on the seat between them; she waves. The camera holds steady.
1.5-3 s: the sofa rises and flies away over the rooftops, getting smaller, and leaves the frame at the top right. The camera stays by the window and tilts up a little after it.
3-6 s: the camera glides forward on its own in a smooth, steady drone flight low over terracotta rooftops, white chimneys and a small square, descending toward a whitewashed house with teal shutters and a lemon tree.
6-8 s: the camera slows and settles on the sunny terrace, framing an empty charcoal mat. The sofa drops into frame from above with both men seated, the turbines blowing glowing exhaust straight down, slows, and hovers half a metre above the mat while the blond man pours crisps from a red packet into the blue bowl. The shot ends on the last frame.
Faces, clothes and props stay the same throughout. Sound: paper bag crinkle, a turbine whine fading into the distance, wind during the flight, swifts and distant church bells, then the whine returning and crisps rattling into a bowl.

Direcione a câmara nos seus próprios planos

O AI Video Production Lab é um workshop ao vivo para pessoas que já geram vídeo com IA e que queiram controlo sobre consistência, referências, movimento de câmara, física e gerações falhadas.

Ver os workshops ↗