{
  "name": "Twistavo tested AI prompt dataset",
  "url": "https://twistavo.com/prompts/dataset",
  "license": "https://creativecommons.org/licenses/by/4.0/",
  "license_scope": "CC BY 4.0 covers the prompt text and row metadata. Linked images and videos are not included in the license.",
  "attribution": "Twistavo, https://twistavo.com/prompts",
  "updated": "2026-11-18",
  "columns": [
    "page_url",
    "example_id",
    "example_title",
    "prompt",
    "model_name",
    "model_id",
    "duration_s",
    "resolution",
    "aspect_ratio",
    "settings",
    "studio_settings",
    "credits",
    "media_url",
    "media_kind",
    "date_tested"
  ],
  "rows": [
    {
      "page_url": "https://twistavo.com/prompts/candid-smartphone-photo",
      "example_id": "laundrette-coin",
      "example_title": "Laundrette: a bodyguard presents one coin (Z-Image Turbo)",
      "prompt": "Candid realistic smartphone photograph inside a modest self-service laundrette. Two original fictional adults: a tiny elegant elderly woman with a sculpted silver beehive hairstyle, angular cream spectacles and a lime-green coat, calmly points to a coin-operated washing machine. Beside her an enormously tall broad-shouldered adult bodyguard in a plain black suit, clean-shaven bald head and discreet earpiece, bows gravely while presenting ONE small laundry coin on a burgundy velvet cushion. A wicker laundry basket is at her feet. The serious palace-level ceremony contrasts with the ordinary washing machines. Both full figures and faces visible. Real skin, natural fluorescent light, no fashion-ad gloss. Vertical photo, no lettering, brands, cartoon or watermark.",
      "model_name": "Z-Image Turbo",
      "model_id": "z-image-turbo",
      "duration_s": "",
      "resolution": "",
      "aspect_ratio": "9:16",
      "settings": "Z-Image Turbo, text to image; Aspect ratio 9:16; Resolution 2k (1152x2048)",
      "studio_settings": "aspectRatio=9:16",
      "credits": 2,
      "media_url": "https://twistavo.com/prompts/candid-smartphone-photo/laundrette-coin.webp",
      "media_kind": "image",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/candid-smartphone-photo",
      "example_id": "checkout-lemon",
      "example_title": "Checkout: a weightlifter squat for one lemon (Z-Image Turbo)",
      "prompt": "Candid full-body smartphone photograph in an ordinary supermarket checkout area. An original fictional short stocky man around sixty, square clean-shaven face, very high silver flat-top hairstyle, huge serious eyebrows, red velvet tracksuit with narrow cream piping and white trainers. He has an intensely focused champion expression and a dramatic weightlifter squat, both hands reaching toward the handles of a comically tiny paper shopping bag containing ONE lemon on the floor. Nearby adult shoppers look quietly puzzled. His build is human and believable. Natural fluorescent supermarket light, real pores and cloth texture, documentary photography, understated absurd comedy. Vertical framing. No readable text, brand, watermark, illustration or cartoon.",
      "model_name": "Z-Image Turbo",
      "model_id": "z-image-turbo",
      "duration_s": "",
      "resolution": "",
      "aspect_ratio": "9:16",
      "settings": "Z-Image Turbo, text to image; Aspect ratio 9:16; Resolution 2k (1152x2048)",
      "studio_settings": "aspectRatio=9:16",
      "credits": 2,
      "media_url": "https://twistavo.com/prompts/candid-smartphone-photo/checkout-lemon.webp",
      "media_kind": "image",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/candid-smartphone-photo",
      "example_id": "wet-sidewalk-pigeon",
      "example_title": "Wet sidewalk: a butler, an umbrella and a pigeon (Z-Image Turbo)",
      "prompt": "Candid full-body smartphone photograph on an ordinary wet city sidewalk. An original fictional tall thin middle-aged butler, long angular clean-shaven face, receding slick black hair, arched eyebrows, immaculate dark teal tailcoat, white gloves and oxblood shoes. With absolute seriousness he holds an elegant black umbrella very low over ONE normal grey pigeon eating crumbs from a small silver plate on the pavement. His own head is outside the umbrella getting wet. Both the man and the tiny bird clearly visible. Natural overcast light, damp wool, real skin pores, realistic street photography. Dry visual comedy, not glamorous advertising. Vertical composition. No writing, logo, watermark, cartoon or illustration.",
      "model_name": "Z-Image Turbo",
      "model_id": "z-image-turbo",
      "duration_s": "",
      "resolution": "",
      "aspect_ratio": "9:16",
      "settings": "Z-Image Turbo, text to image; Aspect ratio 9:16; Resolution 2k (1152x2048)",
      "studio_settings": "aspectRatio=9:16",
      "credits": 2,
      "media_url": "https://twistavo.com/prompts/candid-smartphone-photo/wet-sidewalk-pigeon.webp",
      "media_kind": "image",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/candid-smartphone-photo",
      "example_id": "supermarket-aisle",
      "example_title": "Supermarket aisle: a recurring character portrait (GPT Image 2.5)",
      "prompt": "Create ONE original fictional recurring social-media character in a mundane supermarket aisle, waist-up candid vertical phone photograph, face facing camera with deadpan confidence. Character: Colette, an elegant stocky French woman aged 62, broad square face, light olive skin, deep-set brown eyes, sharp arched eyebrows, long slightly hooked nose and thin unsmiling lips. Her real jet-black hair is arranged in a huge immaculate horizontal crescent-shaped coiffure sweeping outward above both ears like a black crescent moon, with a single narrow silver stripe centered at the hairline. Small rectangular red reading glasses, mustard-yellow sharply tailored skirt suit with very wide square shoulders, cream turtleneck, a rigid oversized burgundy silk neck bow. No props in hands, no gestures or visual gags. Her expression says that this astonishing appearance is completely normal to her. Strong readable human character silhouette, odd but endearing, eccentric not frightening. Real pores, fine age lines, authentic fabric, normal fluorescent supermarket lighting and shelves softly out of focus. Casual unretouched phone capture rather than cinematic or beauty advertising. One image only, no collage, no text, no watermark. Entirely original, no blond bob.",
      "model_name": "GPT Image 2.5",
      "model_id": "gpt-image-2-5",
      "duration_s": "",
      "resolution": "2k",
      "aspect_ratio": "9:16",
      "settings": "GPT Image 2.5 (sunburst), text to image; Aspect ratio 9:16; Quality high; Resolution 2k",
      "studio_settings": "aspectRatio=9:16; quality=high; resolution=2k; variant=sunburst",
      "credits": 20,
      "media_url": "https://twistavo.com/prompts/candid-smartphone-photo/supermarket-aisle.webp",
      "media_kind": "image",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/candid-smartphone-photo",
      "example_id": "laundromat-baguette",
      "example_title": "Laundromat: a baguette held like a scepter (GPT Image 2.5)",
      "prompt": "Photoreal vertical smartphone snapshot at a crowded self-service laundromat in Paris. Center frame: an original fictional French woman in her early 50s, olive skin, an enormous symmetrical silver-gray cloud-shaped bouffant with a sharp straight fringe, a completely deadpan expression, wearing a vivid scarlet 1970s tailored suit with exaggerated pointed white lapels and a single oversized brooch. She sits perfectly upright on a cheap plastic chair and holds one baguette vertically like a ceremonial scepter. Behind her, washing machines spin bright red socks; two ordinary customers in everyday clothes glance over, trying not to stare. The contrast between her theatrical, unmistakable silhouette and the mundane laundromat is immediately funny and slightly uncanny, but still plausible as a candid social-media moment. Straight-on phone-camera framing, a touch of harsh built-in flash, imperfect casual framing, rich natural skin and fabric texture, saturated but realistic colors, crisp readable subject, no editorial glamour and no movie-poster look. No lettering or watermark.",
      "model_name": "GPT Image 2.5",
      "model_id": "gpt-image-2-5",
      "duration_s": "",
      "resolution": "2k",
      "aspect_ratio": "9:16",
      "settings": "GPT Image 2.5 (sunburst), text to image; Aspect ratio 9:16; Quality high; Resolution 2k",
      "studio_settings": "aspectRatio=9:16; quality=high; resolution=2k; variant=sunburst",
      "credits": 20,
      "media_url": "https://twistavo.com/prompts/candid-smartphone-photo/laundromat-baguette.webp",
      "media_kind": "image",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/character-turnaround-sheet",
      "example_id": "hammerhead-sheet",
      "example_title": "Hammerhead-shark bodybuilder, four views (Seedream 4.5)",
      "prompt": "Create a production-ready character turnaround sheet for one entirely original, non-franchise character. EXACTLY FOUR equal-width vertical panels in one clean 3:2 canvas: panel 1 full-body FRONT, panel 2 full-body THREE-QUARTER, panel 3 full-body SIDE PROFILE, panel 4 a large neutral HEAD-AND-SHOULDERS portrait. This is the SAME single character in all four panels. The three full-body figures have identical height, physique, anatomy, costume and scale. Show the complete head and both complete feet with generous margins. The portrait must show the whole head and shoulders, never cropped. Separate panels with empty light-gray space and no drawn borders. No extra view, duplicate, overlapping figure, cut-off limb or fragment.\n\nUse a relaxed upright pose with arms lowered, hands relaxed, eyes naturally forward, closed mouth and neutral expression in EVERY view. Preserve exact facial geometry, skin pattern, body proportions and wardrobe across all views. Render as a tangible stylized cinematic 3D character with detailed materials, soft even studio lighting and a plain light-gray background. No scene, action, flexing, shouting, smile, lettering, numbers, labels, caption, watermark, logo or signature.\n\nORIGINAL CHARACTER: a massive adult humanoid hammerhead-shark bodybuilder with a compact horizontal hammer-shaped head, one small black eye at each outer end, a closed narrow mouth, slate-gray upper skin and a pale-gray underside continuing from jaw to chest. He has a broad muscular human-shaped torso, human-proportioned arms, two consistent five-fingered slate-gray hands, powerful human-shaped legs and feet, and one small dorsal fin. Wardrobe is identical in every view: plain navy short-sleeved polo shirt, plain charcoal trousers and plain black shoes. The clothing has no badge, flag, lettering, stripes, crest or brand. No giant realistic fish body, no tail replacing legs, no extra fins or limbs, no teeth showing, no armor, no accessories, no existing mascot or recognizable copyrighted character.",
      "model_name": "Seedream 4.5",
      "model_id": "seedream-v4-5",
      "duration_s": "",
      "resolution": "",
      "aspect_ratio": "3:2",
      "settings": "Seedream 4.5, text to image; Aspect ratio 3:2; Quality high",
      "studio_settings": "aspectRatio=3:2; quality=high",
      "credits": 9,
      "media_url": "https://twistavo.com/prompts/character-turnaround-sheet/hammerhead-sheet.webp",
      "media_kind": "image",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/character-turnaround-sheet",
      "example_id": "pigeon-sheet",
      "example_title": "Pigeon athlete, four views (Seedream 4.5)",
      "prompt": "Create a production-ready character turnaround sheet for one entirely original, non-franchise character. EXACTLY FOUR equal-width vertical panels in one clean 3:2 canvas: panel 1 full-body FRONT, panel 2 full-body THREE-QUARTER, panel 3 full-body SIDE PROFILE, panel 4 a large neutral HEAD-AND-SHOULDERS portrait. This is the SAME single character in all four panels. The three full-body figures have identical height, physique, anatomy, costume and scale. Show the complete head and both complete feet with generous margins. The portrait must show the whole head and shoulders, never cropped. Separate panels with empty light-gray space and no drawn borders. No extra view, duplicate, overlapping figure, cut-off limb or fragment.\n\nUse a relaxed upright pose with arms lowered, hands relaxed, eyes naturally forward, closed beak and neutral expression in EVERY view. Preserve exact facial geometry, feather pattern, body proportions and wardrobe across all views. Render as a tangible stylized cinematic 3D character with detailed materials, soft even studio lighting and a plain light-gray background. No scene, action, flexing, shouting, smile, lettering, numbers, labels, caption, watermark, logo or signature.\n\nORIGINAL CHARACTER: a massive adult humanoid pigeon bodybuilder with a compact realistic pigeon head, steel-gray crown and face feathers, two vivid orange eyes, a short charcoal-gray beak, and an iridescent emerald-to-violet feather collar around the neck. He has a broad muscular human-shaped torso and limbs covered in short smooth gray feathers, human-proportioned feathered arms, two consistent five-fingered dark-gray hands, powerful legs and a short neat pigeon tail. Wardrobe is identical in every view: plain navy zip-up athletic hoodie with white drawstrings, plain navy athletic trousers and clean white sneakers. The clothing has no badge, flag, lettering, stripes, crest or brand. No wings replacing arms, no bird feet, no extra limbs, no suit, no tie, no accessories, no existing mascot or recognizable copyrighted character.",
      "model_name": "Seedream 4.5",
      "model_id": "seedream-v4-5",
      "duration_s": "",
      "resolution": "",
      "aspect_ratio": "3:2",
      "settings": "Seedream 4.5, text to image; Aspect ratio 3:2; Quality high",
      "studio_settings": "aspectRatio=3:2; quality=high",
      "credits": 9,
      "media_url": "https://twistavo.com/prompts/character-turnaround-sheet/pigeon-sheet.webp",
      "media_kind": "image",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/character-turnaround-sheet",
      "example_id": "homeowner-sheet",
      "example_title": "Photographic person, face and full length (Soul Cinematic)",
      "prompt": "A natural studio character sheet photograph of one beautiful Southeast Asian woman in her late thirties, a homeowner on a relaxed weekend at home, shown twice side by side in two equal vertical panels on one seamless pure-white background. Long straight black hair tied in a low ponytail; a sage-green crew-neck cotton sweater, straight indigo jeans and white canvas sneakers.\nLeft panel: a frontal, eye-level close-up of the face, from just above the top of the head down to the collarbones; the face fills most of the panel, sharp and evenly lit.\nRight panel: the same person full length, standing upright and facing the camera, the whole body from head to toe with both feet flat on the floor and fully visible, arms resting naturally by the sides, a little space above the head and below the feet.\nThe same face, hair and outfit in both panels, a calm, neutral expression and relaxed posture. Subtle everyday makeup and natural skin texture. Soft, even frontal lighting.\nOnly this one presenter and the white background: no other people, no props, no furniture, no text or labels. Horizontal 4:3 photograph.",
      "model_name": "Soul Cinematic",
      "model_id": "soul-cinematic",
      "duration_s": "",
      "resolution": "",
      "aspect_ratio": "",
      "settings": "Soul Cinematic, text to image; Aspect ratio 4:3",
      "studio_settings": "",
      "credits": null,
      "media_url": "https://twistavo.com/prompts/character-turnaround-sheet/homeowner-sheet.webp",
      "media_kind": "image",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/character-turnaround-sheet",
      "example_id": "dog-sidekick-sheet",
      "example_title": "Dog sidekick, full body and portrait (GPT Image 2)",
      "prompt": "Create a photorealistic original DOG character design reference on a plain warm-white background. @Image1 is the approved human style reference ONLY (the red-haired man in the green velvet suit standing before the bakery), not a dog identity. Invent his canine sidekick, not a human face pasted onto a dog. A small slender dog whose defining silhouette mirrors the man's grooming: rich red-ginger fur groomed into two large rounded symmetrical peaks above the ears with a smooth narrow center strip of short fur between them, echoing the man's double-peak hairstyle with bald center. Long narrow light muzzle with pale freckles across the nose bridge, small warm amber eyes, deadpan slightly judgmental expression — the loyal but unimpressed sidekick. Lean small body, four natural canine legs and paws, natural tail. Wardrobe mirroring the man: a green velvet canine jacket with vest-like panels along the back and chest, cream shirt-style collar, small maroon tie detail; functional dog clothing, no human arms, hands or trousers. The visual resemblance to the man comes from the twin red fur peaks, freckled muzzle, velvet green tailoring and deadpan attitude. Reference design sheet: one dominant full-body standing three-quarter view on the left, a head-and-shoulders portrait on the right showing the twin peaks, freckles and expression. Same single dog in both views, complete paws visible. Neutral even lighting, fine real fur, realistic anatomy, clean reference photograph. No human in frame, no setting, no text, no labels, no watermark.",
      "model_name": "GPT Image 2",
      "model_id": "gpt-image-2",
      "duration_s": "",
      "resolution": "2k",
      "aspect_ratio": "16:9",
      "settings": "GPT Image 2, image to image; 1 reference image (style only); Aspect ratio 16:9; Quality medium; Resolution 2k",
      "studio_settings": "aspectRatio=16:9; quality=medium; resolution=2k",
      "credits": 18,
      "media_url": "https://twistavo.com/prompts/character-turnaround-sheet/dog-sidekick-sheet.webp",
      "media_kind": "image",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/character-turnaround-sheet",
      "example_id": "bible-sheet-nano-banana",
      "example_title": "Character bible, one image (Nano Banana 2 Lite)",
      "prompt": "Create a professional character reference sheet for the man shown in the reference images, in a 3:2 landscape layout on a dark charcoal background with thin grey panel borders, like a premium film character bible.\n\nCHARACTER (keep his identity EXACTLY as in the references): CLAUDE, a pale thin man in his 40s with freckles, ginger hair parted in the middle and styled into two tall rounded columns standing straight up on top of his head, round thin gold wire glasses, a thin ginger moustache, grey-green eyes; olive-green velvet three-piece suit (jacket, waistcoat, trousers), cream shirt with a pointed collar, burgundy tie, dark brown leather oxford shoes. The white oval on the full-body reference is only a mask: take his face from the close-up portraits. Same face, same two hair columns, same glasses and same suit in every panel.\n\nLAYOUT, top to bottom:\n1. Top-left title block: the name \"CLAUDE\" in large elegant gold serif capitals with a small gold Eiffel Tower icon above it, and \"CHARACTER SHEET\" underneath. Below it a small info list in white capitals: SPECIES: HUMAN / ROLE: MAIN CHARACTER / VIBE: DANDY, PROUD, DEADPAN / AGE: 40s / HEIGHT: ~5'11\" / BUILD: THIN, LANKY / STYLE: PARISIAN DANDY / PERSONALITY: SNOBBY, FUNNY, UNFLAPPABLE. Next to the list, a small framed head-and-shoulders portrait of him.\n2. The largest row: full-body turnaround, seven views of him standing in a neutral pose on a dark floor, each labeled underneath: FRONT, FRONT 3/4, RIGHT SIDE, BACK 3/4, BACK, LEFT SIDE, LEFT 3/4. His face is fully visible and identical in every front and side view.\n3. A row titled \"CLOSE UP DETAILS\": FACE (FRONT), FACE (SIDE), HAIR (BACK), GLASSES DETAIL, TIE & WAISTCOAT DETAIL, VELVET FABRIC DETAIL, SHOES DETAIL.\n4. Bottom-left block titled \"EXPRESSIONS\": six head-and-shoulders close-ups labeled NEUTRAL, HAPPY, SERIOUS, CONFUSED, ANGRY, SILLY.\n5. Bottom-middle block titled \"POSES / ACTIONS\": four full-body poses: pointing at the camera, dancing with one arm up, arms crossed proudly, walking confidently.\n6. Bottom-right block titled \"REAL WORLD EXAMPLE (IN SCENE)\": three photorealistic photos of him: on a Paris street with Haussmann buildings, inside a Paris metro car, and a close-up selfie-style shot in a café.\n\nStyle: photorealistic, soft studio lighting, natural skin texture with freckles, sharp focus, the same identity in every panel. Clean white sans-serif labels. No brand logos, no trademarks and no other text anywhere: only the title, the info list and the panel labels.",
      "model_name": "Nano Banana 2 Lite",
      "model_id": "nano-banana-2-lite",
      "duration_s": "",
      "resolution": "",
      "aspect_ratio": "3:2",
      "settings": "Made October 6, 2026; Nano Banana 2 Lite, image to image; 2 reference images (a close portrait and a full-body sheet of the character); Aspect ratio 3:2; Thinking high; Resolution 1k",
      "studio_settings": "aspectRatio=3:2; thinking=HIGH",
      "credits": 9,
      "media_url": "https://twistavo.com/prompts/character-turnaround-sheet/bible-sheet-nano-banana.webp",
      "media_kind": "image",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/character-turnaround-sheet",
      "example_id": "bible-sheet-gpt-image",
      "example_title": "Same prompt, clean labels (GPT Image 2.5)",
      "prompt": "Create a professional character reference sheet for the man shown in the reference images, in a 3:2 landscape layout on a dark charcoal background with thin grey panel borders, like a premium film character bible.\n\nCHARACTER (keep his identity EXACTLY as in the references): CLAUDE, a pale thin man in his 40s with freckles, ginger hair parted in the middle and styled into two tall rounded columns standing straight up on top of his head, round thin gold wire glasses, a thin ginger moustache, grey-green eyes; olive-green velvet three-piece suit (jacket, waistcoat, trousers), cream shirt with a pointed collar, burgundy tie, dark brown leather oxford shoes. The white oval on the full-body reference is only a mask: take his face from the close-up portraits. Same face, same two hair columns, same glasses and same suit in every panel.\n\nLAYOUT, top to bottom:\n1. Top-left title block: the name \"CLAUDE\" in large elegant gold serif capitals with a small gold Eiffel Tower icon above it, and \"CHARACTER SHEET\" underneath. Below it a small info list in white capitals: SPECIES: HUMAN / ROLE: MAIN CHARACTER / VIBE: DANDY, PROUD, DEADPAN / AGE: 40s / HEIGHT: ~5'11\" / BUILD: THIN, LANKY / STYLE: PARISIAN DANDY / PERSONALITY: SNOBBY, FUNNY, UNFLAPPABLE. Next to the list, a small framed head-and-shoulders portrait of him.\n2. Top row, the largest: full-body turnaround, seven views of him standing in a neutral pose on a dark floor, each labeled underneath: FRONT, FRONT 3/4, RIGHT SIDE, BACK 3/4, BACK, LEFT SIDE, LEFT 3/4. His face is fully visible and identical in every front and side view.\n3. Middle row titled \"CLOSE UP DETAILS\": FACE (FRONT), FACE (SIDE), HAIR (BACK), GLASSES DETAIL, TIE & WAISTCOAT DETAIL, VELVET FABRIC DETAIL, SHOES DETAIL.\n4. Bottom-left block titled \"EXPRESSIONS\": six head-and-shoulders close-ups labeled NEUTRAL, HAPPY, SERIOUS, CONFUSED, ANGRY, SILLY.\n5. Bottom-middle block titled \"POSES / ACTIONS\": four full-body poses: pointing at the camera, dancing with one arm up, arms crossed proudly, walking confidently.\n6. Bottom-right block titled \"REAL WORLD EXAMPLE (IN SCENE)\": three photorealistic photos of him: on a Paris street with Haussmann buildings, inside a Paris metro car, and a close-up selfie-style shot in a café.\n\nStyle: photorealistic, soft studio lighting, natural skin texture with freckles, sharp focus, the same identity in every panel. Clean white sans-serif labels. No brand logos, no trademarks and no other text anywhere: only the title, the info list and the panel labels.",
      "model_name": "GPT Image 2.5",
      "model_id": "gpt-image-2-5",
      "duration_s": "",
      "resolution": "4k",
      "aspect_ratio": "3:2",
      "settings": "Made October 6, 2026; GPT Image 2.5, image to image; 2 reference images (a close portrait and a full-body sheet of the character); Aspect ratio 3:2; Quality high; Resolution 4k; Variant flare",
      "studio_settings": "aspectRatio=3:2; quality=high; resolution=4k; variant=flare",
      "credits": 28,
      "media_url": "https://twistavo.com/prompts/character-turnaround-sheet/bible-sheet-gpt-image.webp",
      "media_kind": "image",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/faceless-history-video",
      "example_id": "caravan-establishing",
      "example_title": "Shot 1, the hook: a caravan on the dunes at dusk",
      "prompt": "Cinematic vertical 9:16 establishing shot. A vast golden desert at dusk, a distant caravan of camels and merchants silhouetted on the dunes, no faces visible. Camera slowly pushes forward, warm amber light, long shadows, dust in the air. Audio: gentle desert wind, distant camel sounds, no music.",
      "model_name": "Seedance 2.0",
      "model_id": "seedance-2",
      "duration_s": "10",
      "resolution": "720p",
      "aspect_ratio": "9:16",
      "settings": "Seedance 2.0, text to video; Aspect ratio 9:16; Duration 10 s; Resolution 720p; Native audio on (muted on this page)",
      "studio_settings": "aspectRatio=9:16; duration=10; resolution=720p; generateAudio=true; bitrateMode=standard",
      "credits": 386,
      "media_url": "https://twistavo.com/prompts/faceless-history-video/caravan-establishing.mp4",
      "media_kind": "video",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/faceless-history-video",
      "example_id": "souk-glide",
      "example_title": "Shot 2: the market from above",
      "prompt": "Cinematic vertical 9:16 shot. A peaceful ancient Islamic souk at golden hour, merchants in robes trading spices and fabrics, seen from elevated angle, no faces visible, warm light. Camera slowly glides. Audio: soft market ambience, quiet voices distant, no music.",
      "model_name": "Seedance 2.0",
      "model_id": "seedance-2",
      "duration_s": "10",
      "resolution": "720p",
      "aspect_ratio": "9:16",
      "settings": "Seedance 2.0, text to video; Aspect ratio 9:16; Duration 10 s; Resolution 720p; Native audio on (muted on this page)",
      "studio_settings": "aspectRatio=9:16; duration=10; resolution=720p; generateAudio=true; bitrateMode=standard",
      "credits": 386,
      "media_url": "https://twistavo.com/prompts/faceless-history-video/souk-glide.mp4",
      "media_kind": "video",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/faceless-history-video",
      "example_id": "library-glide",
      "example_title": "Shot 3: the library",
      "prompt": "Cinematic vertical 9:16 shot. A grand ancient library with high arches and shelves of old books, warm light streaming through a window, empty, reverent. Camera slowly glides forward between shelves. Audio: soft ambient, faint page rustle, no music.",
      "model_name": "Seedance 2.0",
      "model_id": "seedance-2",
      "duration_s": "10",
      "resolution": "720p",
      "aspect_ratio": "9:16",
      "settings": "Seedance 2.0, text to video; Aspect ratio 9:16; Duration 10 s; Resolution 720p; Native audio on (muted on this page)",
      "studio_settings": "aspectRatio=9:16; duration=10; resolution=720p; generateAudio=true; bitrateMode=standard",
      "credits": 386,
      "media_url": "https://twistavo.com/prompts/faceless-history-video/library-glide.mp4",
      "media_kind": "video",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/faceless-history-video",
      "example_id": "library-still",
      "example_title": "Still: the same library as an image",
      "prompt": "Cinematic documentary still, 9:16 vertical. A grand ancient library with high arches, shelves of old books and manuscripts, warm light streaming through a window, reverent scholarly atmosphere, completely empty of people. No faces, no text, no watermark.",
      "model_name": "Seedream 5.0 Pro",
      "model_id": "seedream-v5-pro",
      "duration_s": "",
      "resolution": "1k",
      "aspect_ratio": "9:16",
      "settings": "Seedream 5.0 Pro, text to image; Aspect ratio 9:16; Resolution 1k",
      "studio_settings": "aspectRatio=9:16; resolution=1k",
      "credits": 11,
      "media_url": "https://twistavo.com/prompts/faceless-history-video/library-still.webp",
      "media_kind": "image",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/faceless-history-video",
      "example_id": "souk-still",
      "example_title": "Still: the market at golden hour",
      "prompt": "Cinematic documentary still, 9:16 vertical. A peaceful ancient Islamic city marketplace at golden hour, merchants and traders in modest robes trading goods, spices, books and wares, seen from elevated angle, figures in long robes, no faces visible, warm sunlight. Sense of exchange, culture and commerce. No text, no watermark.",
      "model_name": "Seedream 5.0 Pro",
      "model_id": "seedream-v5-pro",
      "duration_s": "",
      "resolution": "1k",
      "aspect_ratio": "9:16",
      "settings": "Seedream 5.0 Pro, text to image; Aspect ratio 9:16; Resolution 1k",
      "studio_settings": "aspectRatio=9:16; resolution=1k",
      "credits": 11,
      "media_url": "https://twistavo.com/prompts/faceless-history-video/souk-still.webp",
      "media_kind": "image",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/kling-3-image-to-video",
      "example_id": "cafe-terrace",
      "example_title": "A man steps out of a café and takes a sip",
      "prompt": "Start image (Soul 2, 16:9, 1080p):\nCinematic photo of an adult man in his forties in a plain navy overshirt stepping out of a cafe onto a sunlit terrace holding a cup, medium shot, face clearly visible, warm afternoon light, city street behind, 35mm, absolutely no text, no logos, no prints, no signage\n\nVideo (Kling 3.0 Standard, image to video):\nThe man steps out of the cafe doorway onto the sunlit terrace holding his cup, takes a sip and looks down the street, slow cinematic camera push-in, warm afternoon light, no text",
      "model_name": "Kling 3.0 Standard",
      "model_id": "kling-3-std",
      "duration_s": "5",
      "resolution": "",
      "aspect_ratio": "16:9",
      "settings": "Kling 3.0 Standard, image to video; Start image: the Soul 2 still; Aspect ratio 16:9; Duration 5 s; Sound off; CFG scale 0.5",
      "studio_settings": "aspectRatio=16:9; duration=5; cfgScale=0.5; sound=false",
      "credits": 54,
      "media_url": "https://twistavo.com/prompts/kling-3-image-to-video/cafe-terrace.mp4",
      "media_kind": "video",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/kling-3-image-to-video",
      "example_id": "park-bicycle",
      "example_title": "A woman cycles toward the camera in a park",
      "prompt": "Start image (Soul 2, 16:9, 1080p):\nCinematic photo of an adult woman in her thirties in a plain olive jacket riding a bicycle along a sunny park path lined with trees, medium shot, face clearly visible, relaxed smile, warm morning light, 35mm, absolutely no text, no logos, no prints\n\nVideo (Kling 3.0 Standard, image to video):\nThe woman rides her bicycle toward the camera along the sunny park path, smiling, natural pedalling, the camera tracks backward smoothly, trees and lawn around, warm morning light, no text",
      "model_name": "Kling 3.0 Standard",
      "model_id": "kling-3-std",
      "duration_s": "5",
      "resolution": "",
      "aspect_ratio": "16:9",
      "settings": "Kling 3.0 Standard, image to video; Start image: the Soul 2 still; Aspect ratio 16:9; Duration 5 s; Sound off; CFG scale 0.5",
      "studio_settings": "aspectRatio=16:9; duration=5; cfgScale=0.5; sound=false",
      "credits": 54,
      "media_url": "https://twistavo.com/prompts/kling-3-image-to-video/park-bicycle.mp4",
      "media_kind": "video",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/kling-3-image-to-video",
      "example_id": "avenue-walk",
      "example_title": "A man walks down a sunny avenue",
      "prompt": "Start image (Soul 2, 16:9, 1080p):\nCinematic street photo of an adult man in his thirties wearing a plain white jacket over a plain grey t-shirt with no print, dark jeans, riding a skateboard down a wide sunny city avenue, medium-wide shot, full body and face clearly visible, relaxed smile, tall buildings and trees behind, warm natural daylight, 35mm, absolutely no text, no logos, no prints\n\nVideo (Kling 3.0 Standard, image to video):\nThe man walks confidently toward the camera down the sunny avenue, smiling, natural arm swing, the camera tracks backward smoothly in front of him, cars and trees in the background, warm daylight, no text",
      "model_name": "Kling 3.0 Standard",
      "model_id": "kling-3-std",
      "duration_s": "5",
      "resolution": "",
      "aspect_ratio": "16:9",
      "settings": "Kling 3.0 Standard, image to video; Start image: the Soul 2 still; Aspect ratio 16:9; Duration 5 s; Sound off; CFG scale 0.5",
      "studio_settings": "aspectRatio=16:9; duration=5; cfgScale=0.5; sound=false",
      "credits": 54,
      "media_url": "https://twistavo.com/prompts/kling-3-image-to-video/avenue-walk.mp4",
      "media_kind": "video",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/location-reference-sheet",
      "example_id": "paris-metro-carriage",
      "example_title": "An empty metro carriage on a viaduct, three seated-height views",
      "prompt": "Location reference sheet: a horizontal triptych of three vertical photographs placed side by side and separated by thin white gaps, all showing the same place, completely empty, with no people at all: the inside of a Paris Metro line 6 train car crossing the Bir-Hakeim viaduct over the Seine in bright daylight.\nPanel 1 (left): phone-camera view at seated height looking at a side window: a blue patterned RATP seat and a stainless-steel grab pole in the foreground; through the window, the Eiffel Tower very close across the Seine, framed by the steel structure of the viaduct.\nPanel 2 (center): view down the central aisle toward the back of the car, from the position of a seated passenger taking a selfie: empty blue patterned seats facing each other, vertical stainless-steel grab poles, white ceiling with light strips, a route map strip above the windows; through the right-hand windows, the Eiffel Tower and the river.\nPanel 3 (right): view toward the sliding doors and the windows on the other side: folding seats, door area, the Seine and Paris rooftops outside.\nPhotorealistic, natural daylight, the same interior design and colors in all three panels, no people, no readable text, no labels, no watermark.",
      "model_name": "Nano Banana 2 Lite",
      "model_id": "nano-banana-2-lite",
      "duration_s": "",
      "resolution": "1k",
      "aspect_ratio": "16:9",
      "settings": "Made October 1, 2026; Text to image; Aspect ratio 16:9; Resolution 1k; Thinking HIGH",
      "studio_settings": "aspectRatio=16:9; resolution=1k; thinking=HIGH",
      "credits": 9,
      "media_url": "https://twistavo.com/prompts/location-reference-sheet/paris-metro-carriage.webp",
      "media_kind": "image",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/location-reference-sheet",
      "example_id": "palace-corridor-night",
      "example_title": "An invented palace corridor at night, and a reverse angle that did not happen",
      "prompt": "Location reference sheet, one image with three side-by-side photographic views of the same empty place, thin white gutters between panels, no people, no animals, no text. The place: a long grand marble corridor inside an ancient Arabian Nights sultan's palace at night. Polished cream and grey veined marble floor with long reflections, tall carved marble columns on both sides, pointed horseshoe arches, walls with deep red and gold geometric tapestries, bronze wall torches with real flames giving warm orange light, dark shadows between pools of light, faint incense haze. Panel 1: low ground-level view looking straight down the corridor, floor in the foreground. Panel 2: eye-level view straight down the corridor toward a far golden doorway. Panel 3: reverse angle looking back the other way. Photorealistic, cinematic, moody, consistent lighting in all three panels.",
      "model_name": "Nano Banana 2 Lite",
      "model_id": "nano-banana-2-lite",
      "duration_s": "",
      "resolution": "1k",
      "aspect_ratio": "16:9",
      "settings": "Made October 16, 2026; Text to image; Aspect ratio 16:9; Resolution 1k; Thinking MINIMAL",
      "studio_settings": "aspectRatio=16:9; resolution=1k; thinking=MINIMAL",
      "credits": 9,
      "media_url": "https://twistavo.com/prompts/location-reference-sheet/palace-corridor-night.webp",
      "media_kind": "image",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/location-reference-sheet",
      "example_id": "trocadero-esplanade",
      "example_title": "A Paris esplanade in daylight with a prop placed in one view",
      "prompt": "Location reference sheet, three photorealistic views side by side on one image, of the empty Trocadero esplanade in Paris with the Eiffel Tower across the Seine, bright clear morning light, real photo look. Left view: wide shot from the middle of the esplanade toward the Eiffel Tower, light stone paving, the two curved Palais de Chaillot wings at the edges. Middle view: low camera at ground level looking toward the Eiffel Tower, a small portable football goal with a white net standing on the paving. Right view: reverse angle toward the Palais de Chaillot columns and steps. Absolutely no people, no tourists, no text, no logos, no watermark.",
      "model_name": "Nano Banana 2 Lite",
      "model_id": "nano-banana-2-lite",
      "duration_s": "",
      "resolution": "1k",
      "aspect_ratio": "16:9",
      "settings": "Made October 21, 2026; Text to image; Aspect ratio 16:9; Resolution 1k; Thinking HIGH",
      "studio_settings": "aspectRatio=16:9; resolution=1k; thinking=HIGH",
      "credits": 9,
      "media_url": "https://twistavo.com/prompts/location-reference-sheet/trocadero-esplanade.webp",
      "media_kind": "image",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/miniature-film-set-making-of-ai-video",
      "example_id": "kraken-storyboard",
      "example_title": "Storyboard: the kraken and the model ship (16 panels)",
      "prompt": "UNE PLANCHE DE STORYBOARD PHOTOGRAPHIQUE : exactement SEIZE CASES, QUATRE COLONNES et QUATRE RANGÉES régulières, lecture gauche-droite puis haut-bas. Chaque image est verticale9:16; ensemble vertical9:16. Trois gouttières blanches verticales et trois horizontales rectilignes. Aucun texte, chiffre, légende, logo ou watermark. Les intitulés ci-dessous ne sont pas à imprimer.\n\nPRIORITÉ ABSOLUE : UN DÉCOR MINIATURE FILMÉ PAR DES HUMAINS DE TAILLE NORMALE\nCe n'est PAS un navire grandeur nature avec des acteurs humains normaux dans un gigantesque bassin. C'est un PETIT MONDE VIVANT à échelle réduite, dans un immense studio. Même logique qu'une ville miniature de cinéma observée derrière ses vrais techniciens : les humains modernes et leurs appareils ont leur taille normale; le navire, les Grecs et le Kraken sont tous à une échelle beaucoup plus petite.\nLe navire est une maquette détaillée; un marin grec entier est beaucoup plus petit qu'une main de technicien. Ses habitants sont de minuscules ADULTES réalistes, pas des enfants, pas des figurines immobiles en plastique. Le Kraken est gigantesque à leur échelle, mais lui aussi appartient à la miniature : sa tête émergée reste nettement plus basse qu'un humain moderne, jamais à hauteur de la charpente. Le navire, les Grecs et le monstre conservent ces proportions réduites dans les SEIZE cases; pas de croissance ou de retour soudain à la taille réelle lors de l'attaque.\nLe sujet central est l'ACTION du petit monde, pas la grandeur physique de ses accessoires. Ne pas réduire les techniciens à de minuscules témoins pour agrandir le bateau. Ne pas grossir le décor pour rendre l'action plus importante.\n\nMISE EN SCÈNE ET TROIS PROFONDEURS\nCaméra observatrice B en arrière des réalisateurs, opérateurs et caméra A, à hauteur humaine, recul et perspective naturelle. A visible filme le petit set plus loin dans la même direction. Première profondeur : vrais humains, caméra A, dolly, câbles et consoles. Deuxième : décor maritime miniature détaillé dans un bassin de tournage réduit au sol. Troisième : immense soundstage, hautes charpentes, passerelles, grand cyclorama bleu. Ce n'est ni un extérieur en mer ni une petite boîte de jouets sur une table. Laisser le set central, dégagé entre les silhouettes, sur une large bande du plateau comme une maquette urbaine filmée en studio.\nLa première case établit clairement l'équipe en train de tourner. Ensuite les regards et l'action se portent sur le bateau, les petits Grecs et le Kraken. L'équipe reste un repère de taille/contextualisation et ne vole pas le récit. Des dos ou morceaux de matériel en périphérie suffisent; pas de gros portraits des réalisateurs. B ne se déplace pas au milieu des petits Grecs. Éviter les gros plans qui effacent tout repère d'échelle. Studio monumental n'implique PAS monstres ou acteurs antiques monumentaux.\n\nCONTINUITÉ VISUELLE\nUn seul petit navire inspiré d'une trirème antique : bois sombre, proue avec œil bleu peint, petit éperon de bronze, rames, UN mât, UNE voile pourpre. Huit minuscules Grecs adultes au départ : tuniques écrues, sandales et bronze antique; le capitaine porte une cape rouge sombre et un casque. Corps adultes entiers et poses actives. Aucun marin moderne, bateau européen à plusieurs mâts, pirate ou navire contemporain. Après le broyage, les morceaux gardent leur bois, couleur et œil de proue; aucun navire intact ne revient.\nUn seul petit Kraken mythologique original, humide gris-vert violacé, ventouses ivoire, deux yeux ambrés, bras musculeux reliés au corps. Sa grande gueule DANS SON ÉCHELLE est au ras de l'eau et aspire le courant, les minuscules Grecs et les fragments. Pas portail séparé, monstre qui vise le micro, tourbillon sans cause ni vague utilisée à la place de l'engloutissement. Équipe de trois/quatre adultes modernes en habits sobres, caméra A et matériel ordinaires, toujours hors du petit bassin. Pas fils visibles attachés au monstre ou aux marins.\nAspect de véritable making-of : béton, métal, textiles, eau et bois réalistes, lumières de studio froides/neutres, bronze chaud discret. Pas cartoon, illustration peinte, plastique, fumée cotonneuse. Ne reprendre AUCUN élément nucléaire : aucune ville, bombe, explosion atomique, immeuble ou champignon de fumée. Sujet exclusivement maritime.\n\nLES SEIZE INSTANTS DU MÊME PETIT MONDE\nCASE 01 — Le tournage impossible : Cadrage large de making-of depuis B derrière les techniciens MODERNES à taille normale et caméra A. Plus loin, petit bassin de décor au sol avec une MAQUETTE de navire antique et huit MINUSCULES Grecs adultes vivants à bord. Les Grecs sont beaucoup plus petits que la main des vrais techniciens. Le petit décor est central et lisible entre les silhouettes; grand hangar, hauteur et fond bleu restent évidents. Aucun monstre pour le moment.\nCASE 02 — Action, le navire prend vie : Même caméra observatrice et mêmes proportions. Le réalisateur donne un discret signal prévu Action ! GO !, sans texte imprimé. DANS la maquette, les tout petits Grecs rament et tirent les cordages; voile pourpre gonflée et eau autour de la petite coque. Leur capitaine miniature porte une cape rouge. Ni humains modernes sur le navire ni changement de taille.\nCASE 03 — Tenir le cap : Le petit navire affrontant sa houle devient le centre de l’attention sans devenir grandeur nature. Les minuscules Grecs s’agrippent et manœuvrent; silhouettes modernes et caméra A restent des repères d’échelle sur le bord du cadre. Pas de passage au point de vue intérieur du bateau ni zoom qui efface tous les repères de maquette.\nCASE 04 — Quelque chose sous la coque : Un remous sombre se forme juste sous le petit navire et le dévie. Les Grecs miniatures regardent vers cette cause visible; leurs rames se soulèvent. La menace se raconte dans ce monde réduit, pas par des portraits apeurés de l’équipe.\nCASE 05 — La première tentacule : Un bras du Kraken émerge près de la petite proue et l’agrippe. Ce bras est énorme comparé aux Grecs minuscules, mais reste petit comparé aux vrais humains du tournage. Contact avec le bois et eau qui ruisselle clairement visibles; aucun intérêt pour le micro ou les techniciens.\nCASE 06 — Le monstre mythologique : La tête du Kraken miniature émerge derrière le navire-maquette. Elle domine les Grecs et le petit bateau, MAIS reste nettement plus basse qu’un technicien réel; ce n’est pas un monstre de la hauteur du studio. Ses deux yeux ambrés, ses bras et sa gueule appartiennent à un seul petit corps du décor réduit.\nCASE 07 — Le navire prisonnier : DANS LE DÉCOR MINIATURE, sans modifier les proportions navire/Grecs/Kraken par rapport aux techniciens réels : Deux tentacules se referment AUTOUR de la coque, une autre prend appui sur le plat-bord. Le bateau est soulevé d’un côté; le capitaine et les autres Grecs basculent et s’accrochent. Montrer coque entière, contacts et bras qui la portent, pas bateau flottant sans support.\nCASE 08 — Le bois cède : DANS LE DÉCOR MINIATURE, sans modifier les proportions navire/Grecs/Kraken par rapport aux techniciens réels : La constriction déforme le milieu de la coque et fracture des planches vers l’extérieur. Mât penché, gréement tendu, voile toujours identifiable. Les marins sont encore sur les parties du pont; un rameur perd sa rame. Aucun marin blessé en gros plan, pas de gore; c’est la destruction du bateau qui est spectaculaire.\nCASE 09 — Le Kraken écrase le bateau : DANS LE DÉCOR MINIATURE, sans modifier les proportions navire/Grecs/Kraken par rapport aux techniciens réels : Instant spectaculaire et très lisible : les deux gros bras broient le navire en son milieu, le mât casse et la coque s’ouvre en DEUX parties reliées par quelques planches. Projection de bois, voile qui tombe, grandes gerbes d’eau. Les Grecs chutent vers l’eau entre les fragments en gardant des corps entiers, sans sang.\nCASE 10 — La gueule aspire la mer : DANS LE DÉCOR MINIATURE, sans modifier les proportions navire/Grecs/Kraken par rapport aux techniciens réels : Le Kraken abaisse et ouvre sa LARGE GUEULE CENTRALE sombre à la surface entre ses bras, juste devant les fragments. L’eau forme un entonnoir dirigé dans cette gueule : origine de l’aspiration visible, pas un portail indépendant. Les deux morceaux du navire et les huit Grecs encore visibles dans/au bord de l’eau sont entraînés vers elle.\nCASE 11 — Le courant gagne : DANS LE DÉCOR MINIATURE, sans modifier les proportions navire/Grecs/Kraken par rapport aux techniciens réels : Le même vortex attire rames, voile et fragments vers la bouche. Les Grecs nagent ou s’agrippent aux débris mais glissent dans la MÊME direction. Capitaine rouge reconnaissable sur un fragment à droite. Les silhouettes restent distinctes du bois; aucun technicien moderne dans ce courant.\nCASE 12 — Les premiers sont aspirés : Les deux premiers petits Grecs sont happés avec l’eau par le bord de la gueule du Kraken miniature; les autres restent sur la spirale en amont. Le repère humain moderne ou le bord du petit décor reste dans le cadrage; ne pas transformer ce moment en plan de bateau/monstre grandeur nature.\nCASE 13 — Toute la troupe entraînée : DANS LE DÉCOR MINIATURE, sans modifier les proportions navire/Grecs/Kraken par rapport aux techniciens réels : La plupart des Grecs sont maintenant aspirés vers la gueule avec les morceaux du bateau, suivant le courant convergent. Montrer plusieurs silhouettes antiques distinctes dans le flux, sans membres détachés. Seuls le capitaine rouge et deux compagnons restent encore en amont. La catastrophe ne s’arrête pas à des éclaboussures.\nCASE 14 — Le dernier capitaine : Dernier petit Grec visible : le capitaine à cape rouge lâche la proue miniature brisée et est emporté vers la petite gueule. Les autres ont déjà été engloutis et ne réapparaissent pas. Garder son échelle minuscule par rapport aux techniciens modernes et à caméra A.\nCASE 15 — Tous engloutis : Le capitaine miniature et le dernier gros fragment de maquette franchissent le bord de la gueule dans l’écume. Aucun autre Grec oublié dans l’eau, aucun bateau intact. Pas de gros plan anatomique, de sang ou de corps déchiré.\nCASE 16 — La scène après le désastre : Vue finale du même petit bassin : le Kraken reste un monstre DE MAQUETTE par rapport aux techniciens adultes normaux qui filment. Le petit navire est détruit et TOUS ses Grecs ont disparu dans la gueule : ZÉRO Grec dans l’eau, ZÉRO capitaine/cape portée restante, ZÉRO navire intact. Seulement eau agitée et quelques menus débris inanimés. Même immense studio autour. La catastrophe miniature est le sujet, pas une réaction du réalisateur.\n\nVÉRIFICATION FINALE : 4colonnes×4rangées,16images; maquette+minusculesGrecs+petitKraken face à des techniciens NORMAUX; histoire lisible sur ce petit monde; navire broyé, marins aspirés dans la gueule puis AUCUN restant à la dernière case. Sans sang, gore, organes ou démembrement. Pas de changement d'échelle pour dramatiser. Aucun texte imprimé.\n",
      "model_name": "GPT Image 2.5",
      "model_id": "gpt-image-2-5",
      "duration_s": "",
      "resolution": "4k",
      "aspect_ratio": "9:16",
      "settings": "Made with GPT Image 2.5, September 30, 2026; Text to image; Aspect ratio 9:16; Quality high; Resolution 4k",
      "studio_settings": "aspectRatio=9:16; quality=high; resolution=4k; background=opaque; variant=sunburst",
      "credits": 28,
      "media_url": "https://twistavo.com/prompts/miniature-film-set-making-of-ai-video/kraken-storyboard.webp",
      "media_kind": "image",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/miniature-film-set-making-of-ai-video",
      "example_id": "kraken-making-of",
      "example_title": "The kraken take: start and end image",
      "prompt": "MAKING-OF CINÉMATOGRAPHIQUE D'UN PETIT MONDE MYTHOLOGIQUE VIVANT. Le récit appartient au navire grec et à ses minuscules habitants : le Kraken broie leur bateau, puis les aspire TOUS. Les techniciens normaux donnent l'échelle et filment, sans devenir la cible ni le gag.\nRÉFÉRENCES : @Image1 est la première frame, avec petit navire intact, Grecs et équipe réelle; elle fixe monde, proportions et départ, PAS l'immobilité. @Image2 est la dernière frame : même bassin, Kraken, seuls débris, aucun Grec restant. Relier ces deux états par de vraies actions, pas un fondu. Même créature, bateau, studio, caméra A et techniciens. Remplir le cadre sans bordure.\nÉCHELLE INVARIANTE : navire-maquette, minuscules Grecs ADULTES vivants en tuniques claires/bronze, capitaine à cape rouge, pas figurines rigides. Un Grec est beaucoup plus petit qu'une main de technicien. Le Kraken est immense POUR EUX mais reste à l'échelle réduite du décor, pas un monstre de la hauteur du hangar. Aucun agrandissement du bateau, des Grecs ou du Kraken pour dramatiser. Les techniciens modernes gardent leur taille normale; ne pas les rétrécir.\nGÉOGRAPHIE/CAMÉRA : B observe derrière l'équipe et la caméra A dirigée vers le bassin. Premier plan : vrais techniciens et matériel; milieu : petit bassin/navire; fond : vaste hangar, charpente haute et cyclorama bleu. Une prise continue, perspective naturelle, légère dérive humaine sur le même côté. Garder le rebord du bassin et du matériel/une silhouette moderne comme repères pendant l'attaque. Pas de portrait du réalisateur, macro dans le petit monde, contrechamp ou cut qui fait oublier la miniature. Le set reste central, dégagé et net; les dos ne masquent pas le naufrage. Se rapprocher/recentrer très modérément puis rejoindre naturellement la vue finale, sans saut de caméra.\nACTION, budgets temporels indicatifs :\n0–2s : déjà le bateau et les petits Grecs au travail, rames et cordages bougent, voile pourpre frémit. Geste puis commande du réalisateur. Aucun Kraken avant le signal.\n2–6s : remous local sous le bateau. Une tentacule émerge, ruisselle et agrippe la proue à œil peint. La tête du même Kraken sort derrière, ses bras se referment autour de la coque. Les Grecs cessent de ramer et cherchent appui, capitaine accroché au bord.\n6–11s : contraction visible des bras AU CONTACT du bois. Coque qui plie, planches qui cassent, mât qui cède, bateau broyé en deux morceaux. Les Grecs perdent l'équilibre et tombent dans l'eau avec les débris; corps entiers. Pas une disparition du bateau derrière un jet opaque.\n11–17s : gueule centrale ouverte au ras de l'eau, reliée au Kraken. Elle aspire l'eau : vortex convergent, planches et Grecs entraînés dans la MÊME direction. Les petits marins tentent de s'accrocher, puis sont happés un à un. Le capitaine rouge est le dernier à passer le bord de la gueule. Montrer ces trajets, ni téléportation ni simple plongée hors cadre.\n17–20s : tous les Grecs ont été engloutis, aucun corps/casque/cape portée restant dans l'eau; navire détruit sans reset. Kraken et quelques débris dans le bassin turbulent, équipe filmant ce désastre miniature. Rejoindre l'état final sans figer l'eau, le monstre ou les humains.\nPHYSIQUE/SON : eau liquide, écume fine, gouttes balistiques, inertie du bateau, bois qui résiste avant de céder. Sans fil porteur, morphing, corps fusionnés, gore ou nuage cotonneux. Audio natif : le réalisateur seul dit en français « Action ! GO ! » une fois au début. Puis rames, eau, craquements synchronisés, grondement et aspiration, cris brefs non verbaux des petits Grecs. Réactions du crew secondaires. Sans musique, voix off, texte, logo ni watermark.",
      "model_name": "Seedance 2.5",
      "model_id": "seedance-2.5",
      "duration_s": "20",
      "resolution": "480p",
      "aspect_ratio": "9:16",
      "settings": "Made with Seedance 2.5, September 30, 2026; Start image and end image (2 uploads); Aspect ratio 9:16; Duration 20 s; Resolution 480p; Audio on (native)",
      "studio_settings": "aspectRatio=9:16; duration=20; resolution=480p; generateAudio=true; bitrateMode=standard",
      "credits": 515,
      "media_url": "https://twistavo.com/prompts/miniature-film-set-making-of-ai-video/kraken-making-of.mp4",
      "media_kind": "video",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/miniature-film-set-making-of-ai-video",
      "example_id": "shadow-giant-storyboard",
      "example_title": "Storyboard: the director's shadow comes alive (16 panels)",
      "prompt": "Créer UNE GRANDE PLANCHE DE STORYBOARD PHOTOGRAPHIQUE, EXACTEMENT SEIZE IMAGES en grille régulière QUATRE COLONNES × QUATRE RANGÉES. Chaque case verticale 9:16, planche verticale 9:16. Lecture gauche-droite puis haut-bas. Trois gouttières verticales et trois gouttières horizontales blanches fines, nettes et régulières. Aucun titre, chiffre, texte, bulle, légende, logo, watermark ou fin-carton généré. Les numéros qui suivent sont des instructions, pas du texte à imprimer. Pas de case fusionnée, pas de duplication de case, pas de case en plus.\n\nC’est un NOUVEAU sujet, pas la précédente explosion : ne dessiner ni bombe, ni champignon, ni ancienne ville. Image sans référence jointe ; la description ci-dessous définit intégralement cette nouvelle fiction.\n\nPOV APPROUVÉ : MAKING-OF DU MAKING-OF\nNotre caméra B observe de l’ARRIÈRE, un peu reculée derrière les cinéastes et leur caméra A. Dans CHAQUE CASE, les dos ou trois-quarts dos de l’équipe et la caméra de cinéma A doivent précéder le décor filmé. B ne devient JAMAIS la caméra A, ne rentre jamais dans le décor, ne montre jamais l’image tournée par A, pas d’insert, pas de champ-contrechamp ni de portraits frontaux. Même axe, même focale grand-angle naturelle, même côté du studio, seul un recul discret de B au dernier tiers est permis. Ce sont seize moments d’une même action continue d’environ vingt secondes, pas seize posters différents.\n\nCONTINUITÉ\nQuatre adultes récurrents, adultes plausibles de taille normale, décrits une fois et inchangés : à gauche opérateur en casquette noire et tenue sombre devant des moniteurs ; centre-gauche réalisateur chauve en veste anthracite et pantalon sombre ; centre technicienne en veste moutarde/ocre, chignon et pantalon sombre, même tablette ; centre-droit cadreur en polo bleu marine, cargo beige, sur une caméra noire A montée sur dolly. Garder vêtements, silhouettes et cheveux cohérents entre toutes les cases, pas de foule ni de cinquième opérateur. Leurs réactions sont causées par l’effet, jamais la panique avant le départ. A pointe vers le set derrière eux. Moniteurs à gauche, rails de A à droite, câbles au sol, deux flight-cases dans la zone de prise ; garder leur position et leurs proportions jusqu’à un mouvement explicitement demandé. L’observateur B n’apparaît pas comme personnage.\n\nÉCHELLE\nStudio réellement monumental : charpente très haute, passerelles et plafonds lointains, longs volumes, grands cycloramas bleus visibles AUTOUR du décor. Les personnages et la caméra servent de repères de taille. Décor important construit AU SOL, présent au milieu de l’image, pas une petite table ou une île distante après une dalle vide. Profondeur claire : B → équipe/A → set → cyclorama/charpente. Conserver les mêmes dimensions apparentes et relations spatiales à travers la grille. Ne jamais agrandir un petit objet artificiellement pour fabriquer le spectaculaire : les évolutions prescrites sont physiques et causales. Garder le hangar, A et au moins trois silhouettes reconnaissables même à la fin, sans tout cacher par la fumée, la neige ou la lumière.\n\nDÉPART\nCases 01–02 : préparation déjà intrigante mais calme. Case03 : geste du réalisateur pour la réplique prévue « Action ! GO ! », aucune parole écrite. L’effet ne commence qu’en case04. Cas04–08 : premier effet dans le décor, réactions professionnelles. Cases09–12 : événement dépasse le test, surprise graduelle et vrai contact avec le plateau. Cases13–16 : réactions plus fortes et conséquence finale propre au sujet. Pas de blessés, pas de mort, pas de sang. Prévu sans musique ; images fixes ne représentent pas une preuve d’audio.\n\nÉPISODE : L’ombre qui n’obéit plus\nGENRE : Horreur sans gore\nINTENTION : Le réalisateur déclenche le tournage ; son ombre projetée sur le cyclorama continue à bouger même quand lui se fige.\n\nDÉCOR ET OBJET VERROUILLÉS\nUn immense studio cinéma avec cyclorama bleu-gris, vaste charpente, projecteurs et plateau en béton. Au milieu, décor ouvert de manoir fictif : porte en bois noir, deux murs latéraux et escalier court, aucun personnage additionnel. Une source de lumière technique stable sur le côté projette au début les ombres normales du crew. Après le signal, UNE ombre noire du réalisateur se met à agir de façon indépendante puis grandit sur le cyclo. Ombre de silhouette humaine crédible, pas texte, pas démon dessiné, pas tête de monstre en 3D, pas yeux rouges. Le réalisateur réel garde ses vêtements anthracite, sa tête chauve et une taille normale ; aucun double physique. Aucun sang ni arme. L’ombre reste principalement visible sur le cyclorama loin derrière le décor, dans notre même plan making-of.\n\nLES SEIZE INSTANTS, DANS CET ORDRE\n\nRANGÉE 1\nCASE01 : Plateau de manoir prêt, lumière stable, crew calme de dos, ombres ordinaires sur le cyclo, caméra A orientée vers la porte.\nCASE02 : Le cadreur se met en position, technicienne à la tablette, réalisateur debout sans geste étrange.\nCASE03 : Le réalisateur lève le bras pour Action ! GO ! ; son ombre reproduit encore exactement ce geste.\nCASE04 : Le bras réel redescend, mais le bras de son ombre reste levé sur le cyclo : premier décalage lisible.\n\nRANGÉE 2\nCASE05 : Le réalisateur tourne légèrement la tête, tandis que l’ombre agite lentement sa main restée en l’air.\nCASE06 : Le vrai réalisateur se fige ; la source de lumière ne bouge pas et son ombre continue seule.\nCASE07 : La technicienne relève la tête vers le cyclo, le cadreur garde A tournée vers le décor.\nCASE08 : L’ombre allonge doucement son cou et ses épaules sur le mur, silhouette encore humaine, pas un nouvel acteur.\n\nRANGÉE 3\nCASE09 : Le réalisateur fait un petit geste pour vérifier, l’ombre fait un mouvement différent, la dissociation est claire.\nCASE10 : La silhouette noire grandit au-dessus des murs du manoir sans couvrir la charpente entière.\nCASE11 : L’ombre se penche au-dessus du décor comme pour inspecter A, technicienne reculant d’un pas.\nCASE12 : Le vrai réalisateur garde les deux mains près du corps, alors que les mains de l’ombre se lèvent indépendamment.\n\nRANGÉE 4\nCASE13 : Le cadreur lâche son viseur et regarde la silhouette, caméra A reste dans le même axe.\nCASE14 : Les quatre cinéastes reculent vers les flight-cases ; le manoir, rails et moniteurs demeurent en place.\nCASE15 : L’ombre énorme se rapproche visuellement du cadre par une projection plus grande, crew à couvert sans personne supplémentaire.\nCASE16 : Payoff large : crew figé derrière les caisses, l’ombre géante salue tranquillement la caméra A depuis le cyclorama, le réalisateur réel n’a aucun bras levé ; making-of horrifique, sans gore.\n\nRENDU ET CONTRÔLE FINAL\nAspect d’une photographie de making-of de cinéma haut de gamme : lumière volumétrique crédible, peau et textiles naturels, métal/câbles/sol/matériaux usés plausibles. Pas illustration, dessin, toon, jeu vidéo, poster, look plastique ou collage. Physique et anatomie lisibles, mouvements différenciés d’une case à l’autre. Contraste froid du studio conservé, accent lumineux propre au sujet, aucune dominante orange artificielle sur tous les épisodes. Faire de la première case une vraie mise en place et de la dernière un vrai payoff, pas une image de titre. La progression, les props et le décor doivent être exactement ceux décrits. Le même cadre making-of arrière demeure le fil conducteur des SEIZE cases. EXACTEMENT4colonnes×4rangées, seize cases verticales 9:16, aucun texte imprimé.\n",
      "model_name": "GPT Image 2.5",
      "model_id": "gpt-image-2-5",
      "duration_s": "",
      "resolution": "4k",
      "aspect_ratio": "9:16",
      "settings": "Made with GPT Image 2.5, September 30, 2026; Text to image; Aspect ratio 9:16; Quality high; Resolution 4k",
      "studio_settings": "aspectRatio=9:16; quality=high; resolution=4k; background=opaque; variant=sunburst",
      "credits": 28,
      "media_url": "https://twistavo.com/prompts/miniature-film-set-making-of-ai-video/shadow-giant-storyboard.webp",
      "media_kind": "image",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/miniature-film-set-making-of-ai-video",
      "example_id": "shadow-giant-making-of",
      "example_title": "The shadow take: start image and two references",
      "prompt": "MAKING-OF DU MAKING-OF, cinéma photoréaliste et humour de catastrophe. Une prise continue : préparation, événement, conséquences, réaction. Ni diaporama ni seize cuts.\nRÔLES : @Image1 fixe la composition initiale, pas l'immobilité. @Image2 définit l'apparence/échelle du sujet ou effet. @Image3 définit la situation finale souhaitée, PAS une frame finale figée. Même monde et mêmes personnes, pas trois scènes. Ignorer les petites marges; animer gestes, matières et réactions en plein cadre sans bordure.\nGÉOGRAPHIE : notre caméra B observe DEPUIS DERRIÈRE l'équipe et sa caméra A, dirigée vers le set plus loin. Opérateur en noir aux moniteurs gauche ; réalisateur chauve anthracite centre-gauche ; technicienne chignon/veste ocre au centre ; cadreur marine/cargo beige avec A sur dolly à droite. Garder quatre adultes, leurs vêtements, le set et ses côtés. Éclairage de plateau, charpente très haute, lointain cyclorama bleu, rails et flight-cases visibles : immense volume, jamais petite pièce. Les personnages vus de dos/3-4 dos regardent l'événement, pas B.\nCAMÉRA : B reste derrière l'équipe, en plan large documentaire, perspective naturelle et micro-mouvements humains. Elle ne devient jamais la vue de A. Pas de zoom, insert, contrechamp ni coupe. Au danger B recule/s'abaisse légèrement sur le même axe; l'action cause sa réaction.\n\nACTION ET PHYSIQUE, temps indicatifs continus :\n0–2s : façade de manoir en décor, grand cyclorama et équipe visibles; éclairage latéral constant. Petite ombre ordinaire ou à peine visible. Le réalisateur donne le signal pendant que A cadre le set.\n2–6s : l'ombre du réalisateur s'allonge sur le cyclorama, puis lève un bras alors que son bras réel est déjà baissé. Montrer simultanément son corps et cette contradiction. L'ombre reste une lumière occultée sur les surfaces, pas un monstre en chair debout dans le studio.\n6–11s : silhouette très grande, penumbra douce sur le mur, mains et tête lisibles; elle se penche puis ouvre les deux bras. Le réalisateur vérifie sa propre main puis regarde le mur. La technicienne tourne vivement les yeux et le torse, le cadreur interrompt son réglage. La lumière des projecteurs et le décor ne changent pas pour expliquer le gag.\n11–16s : l'ombre s'abaisse et se replie près de la façade puis remonte plus grande, sa projection suivant les angles du mur/sol sans traverser le décor. Le crew se recule et se baisse en décalé derrière A et les caisses, talons qui raclent, mains protégeant les têtes, un ou deux cris brefs; l'ombre ne les touche pas. B s'abaisse avec eux mais reste derrière.\n16–20s : l'immense silhouette se redresse et lève UNE main ouverte, faisant un petit coucou autonome au-dessus du crew accroupi. Le réalisateur ne fait pas ce salut. Fin sur ce contraste : la projection joue la star et l'équipe reste à couvert. Pas de clapboard, d'entité 3D, de nouveaux humains, de brusque extinction ni flash pour cacher un raccord. L'ombre conserve sa forme humaine, pas de doigts qui se multiplient. SFX : room tone du plateau, ballast léger, vêtements, pas, respiration et cris; pas de musique d'horreur.\n\nJEU ET RENDU : réactions décalées entre personnes, mains occupées à protéger le matériel, transfert du poids, regards suivant la cause, souffle et récupération. Contacts solides, gravité/inertie cohérentes hors anomalie voulue, matières détaillées, ombres de contact et occultations naturelles. Pas de figurants nouveaux, de corps fusionnés, d'immobilité ou de reset du décor; aucun fil porteur. Ni ralenti, timelapse, fumée cotonneuse, filtre jeu vidéo, texte, sous-titre, logo généré ou musique. La dernière seconde reste vivante.\nAUDIO NATIF : au début, le réalisateur seul lance en français {Action ! GO !}, une fois, voix masculine adulte projetée vers le set. Ensuite bruitages causaux synchronisés, pas/respirations, un ou deux cris brefs spontanés des techniciens quand le danger arrive; pas chœur ni voix off. Le son garde l'acoustique vaste du studio, sans saturation.",
      "model_name": "Seedance 2.5",
      "model_id": "seedance-2.5",
      "duration_s": "20",
      "resolution": "480p",
      "aspect_ratio": "9:16",
      "settings": "Made with Seedance 2.5, September 30, 2026; Start image and 2 reference images (3 uploads); Aspect ratio 9:16; Duration 20 s; Resolution 480p; Audio on (native)",
      "studio_settings": "aspectRatio=9:16; duration=20; resolution=480p; generateAudio=true; bitrateMode=standard",
      "credits": 515,
      "media_url": "https://twistavo.com/prompts/miniature-film-set-making-of-ai-video/shadow-giant-making-of.mp4",
      "media_kind": "video",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/miniature-film-set-making-of-ai-video",
      "example_id": "pompeii-making-of",
      "example_title": "Pompeii in miniature: two references, no start image",
      "prompt": "MAKING-OF D'UNE POMPÉI MINIATURE VIVANTE. Le marché romain devient une catastrophe : le Vésuve entre en éruption, une nuée dévale ses pentes, détruit la ville puis laisse les mêmes rues sous les cendres. Le récit appartient au petit monde; l'équipe moderne donne l'échelle et filme, sans devenir le gag.\nRÉFÉRENCES : @Image1 définit la ville intacte, ses habitants, le studio et les proportions au départ. @Image2 définit seulement les dégâts et l'état final du MÊME lieu. Ces images ne sont pas deux plans à coller ni des frames à figer : animer une action physique continue entre ces états. Conserver les lieux et proportions sans étirer les images ni copier leurs marges. Fontaine centrale, auvent rouge à gauche, temple à droite, Vésuve derrière la ville; garder cette géographie.\nÉCHELLE : techniciens modernes ADULTES de taille normale; cité, volcan et Romains ADULTES entièrement miniatures. Un Romain est plus petit qu'une main de technicien, les toits bien plus bas que sa taille, le cône sous ses épaules. Le panache peut dominer ce petit monde mais ne remplit pas le hangar. Habitants vivants, articulés, pas des figurines rigides; aucun agrandissement de la ville ou du volcan, aucun rétrécissement du crew.\nCAMÉRA : une seule prise observatrice B derrière la caméra A et l'équipe, même côté du set. Perspective humaine naturelle, cadrage large stable avec une légère dérive, décor net et central. Caméra A et une silhouette moderne restent en périphérie comme repères; charpente haute et fond bleu visibles. Pas de zoom dans les rues, portrait du réalisateur, extérieur réel ou saut d'axe. Les dos ne cachent pas la scène.\nACTION, budgets temporels indicatifs :\n0–2s : marché déjà vivant, Romains qui marchent, étoffes qui bougent, eau de la fontaine. Le réalisateur donne le signal; le volcan est encore calme.\n2–6s : secousse dans la ville, eau qui tremble, une amphore tombe, habitants qui cherchent appui puis regardent le volcan. Une fumée sombre sort DU cratère, puis une colonne de cendres éclate avec quelques grains incandescents à sa base.\n6–11s : le bas du panache s'effondre sur la pente; un front dense de cendres descend depuis le volcan VERS les quartiers arrière. Les Romains fuient vers l'avant gauche, à l'opposé du danger, une charrette est abandonnée. Montrer le front frapper les premières maisons, soulever leurs tuiles et casser un toit AVANT de les masquer.\n11–16s : le même front traverse la rue et atteint le forum. Auvent rouge arraché de ses poteaux, charrette renversée, petits murs qui cèdent; une partie du fronton et des colonnes du temple s'effondre sous l'impact. Les derniers petits habitants sont masqués par les cendres, sans blessure montrée. Dommages persistants, pas une ville intacte derrière un voile de fumée.\n16–20s : la nuée se dissipe assez pour révéler la ville ravagée : toits écroulés, gravats et rues remplies de cendres, fontaine encore identifiable, restes du marché et colonnes à leur place. Aucun habitant identifiable, aucun reset. Le petit volcan fume encore, des particules retombent, les techniciens continuent de filmer; fin vivante sur les ruines, pas arrêt sur image.\nMATIÈRE/SON : cendres gris-brun granuleuses, front turbulent collé au relief, débris avec poids et inertie, contacts et effondrements visibles. Pas mousse cotonneuse, lave qui remplace la nuée, explosion atomique, morphing ou gore. Lumière de studio neutre, chaleur discrète sur la cité. Audio natif : le réalisateur seul dit en français « Action ! GO ! » UNE fois au début; puis marché, secousses, volcan, tuiles, souffle et cris lointains non verbaux. Crew secondaire. Sans musique, narration, texte, logo ni watermark.",
      "model_name": "Seedance 2.5",
      "model_id": "seedance-2.5",
      "duration_s": "20",
      "resolution": "480p",
      "aspect_ratio": "9:16",
      "settings": "Made with Seedance 2.5, September 30, 2026; 2 reference images (intact town, ruined town); Aspect ratio 9:16; Duration 20 s; Resolution 480p; Audio on (native)",
      "studio_settings": "aspectRatio=9:16; duration=20; resolution=480p; generateAudio=true; bitrateMode=standard",
      "credits": 515,
      "media_url": "https://twistavo.com/prompts/miniature-film-set-making-of-ai-video/pompeii-making-of.mp4",
      "media_kind": "video",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/miniature-film-set-making-of-ai-video",
      "example_id": "ufo-making-of",
      "example_title": "The levitation take: the gag leaves the miniature",
      "prompt": "MAKING-OF DU MAKING-OF, cinéma photoréaliste et humour de catastrophe. Une prise continue : préparation, événement, conséquences, réaction. Ni diaporama ni seize cuts.\nRÔLES : @Image1 fixe la composition initiale, pas l'immobilité. @Image2 définit l'apparence/échelle du sujet ou effet. @Image3 définit la situation finale souhaitée, PAS une frame finale figée. Même monde et mêmes personnes, pas trois scènes. Ignorer les petites marges; animer gestes, matières et réactions en plein cadre sans bordure.\nGÉOGRAPHIE : notre caméra B observe DEPUIS DERRIÈRE l'équipe et sa caméra A, dirigée vers le set plus loin. Opérateur en noir aux moniteurs gauche ; réalisateur chauve anthracite centre-gauche ; technicienne chignon/veste ocre au centre ; cadreur marine/cargo beige avec A sur dolly à droite. Garder quatre adultes, leurs vêtements, le set et ses côtés. Éclairage de plateau, charpente très haute, lointain cyclorama bleu, rails et flight-cases visibles : immense volume, jamais petite pièce. Les personnages vus de dos/3-4 dos regardent l'événement, pas B.\nCAMÉRA : B reste derrière l'équipe, en plan large documentaire, perspective naturelle et micro-mouvements humains. Elle ne devient jamais la vue de A. Pas de zoom, insert, contrechamp ni coupe. Au danger B recule/s'abaisse légèrement sur le même axe; l'action cause sa réaction.\n\nACTION ET PHYSIQUE, temps indicatifs continus :\n0–2s : capsule argentée posée sur son socle circulaire, plateau spatial visible. L'équipe règle A et le réalisateur donne son signal; pas de lévitation avant.\n2–6s : le halo pratique sous la capsule s'allume et la capsule entière monte lentement de quelques dizaines de centimètres, puis plus haut. Une seule capsule, taille et forme constantes, ombre qui s'écarte de son dessous. Aucun fil de portage.\n6–10s : l'anomalie gagne le matériel proche : d'abord chiffon et rouleau, puis petite caisse. Ils quittent le sol progressivement avec faible rotation et inertie; ni explosion ni téléportation. Le réalisateur suit l'objet des yeux et tend la main sans le rattraper; la technicienne retient sa tablette contre elle.\n10–16s : le dolly, sa caméra A et le cadreur assis se soulèvent en un ensemble cohérent au-dessus des rails restés au sol. Les câbles prennent du mou puis décrivent des courbes pesantes, sans traverser les corps. Le cadreur agrippe les poignées, chaussures cherchant un appui; le réalisateur essaie de le retenir puis perd à son tour l'appui. Cris courts et respirations vraiment liés à la perte de poids.\n16–20s : capsule au fond, A/cadreur et une partie du crew flottent bas au-dessus du plateau avec quelques accessoires. La technicienne reste lisible avec sa tablette. Mains et pieds font de petites corrections désordonnées; aucun vol héroïque synchronisé. Fin sur une équipe essayant encore de tourner en apesanteur. B reste au sol derrière la limite de cette anomalie, le plafond et les rails ancrent l'échelle. SFX : machine qui monte en régime, roues décollant des rails, câbles, accessoires et souffles, sans nappe musicale.\n\nJEU ET RENDU : réactions décalées entre personnes, mains occupées à protéger le matériel, transfert du poids, regards suivant la cause, souffle et récupération. Contacts solides, gravité/inertie cohérentes hors anomalie voulue, matières détaillées, ombres de contact et occultations naturelles. Pas de figurants nouveaux, de corps fusionnés, d'immobilité ou de reset du décor; aucun fil porteur. Ni ralenti, timelapse, fumée cotonneuse, filtre jeu vidéo, texte, sous-titre, logo généré ou musique. La dernière seconde reste vivante.\nAUDIO NATIF : au début, le réalisateur seul lance en français {Action ! GO !}, une fois, voix masculine adulte projetée vers le set. Ensuite bruitages causaux synchronisés, pas/respirations, un ou deux cris brefs spontanés des techniciens quand le danger arrive; pas chœur ni voix off. Le son garde l'acoustique vaste du studio, sans saturation.",
      "model_name": "Seedance 2.5",
      "model_id": "seedance-2.5",
      "duration_s": "20",
      "resolution": "480p",
      "aspect_ratio": "9:16",
      "settings": "Made with Seedance 2.5, September 30, 2026; Start image and 2 reference images (3 uploads); Aspect ratio 9:16; Duration 20 s; Resolution 480p; Audio on (native)",
      "studio_settings": "aspectRatio=9:16; duration=20; resolution=480p; generateAudio=true; bitrateMode=standard",
      "credits": 515,
      "media_url": "https://twistavo.com/prompts/miniature-film-set-making-of-ai-video/ufo-making-of.mp4",
      "media_kind": "video",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/recurring-ai-character-cast",
      "example_id": "claude-portrait",
      "example_title": "CLAUDE is born: a phone-style portrait outside a bakery (GPT Image 2.5)",
      "prompt": "Create ONE original fictional recurring social-media character, photographed on a normal city pavement outside a mundane neighborhood bakery. Waist-up vertical casual phone photo, eye level, looking directly at camera. Character: Lucien, a lanky French man aged 45 with a long narrow face, prominent ears, pale freckled skin and tiny round gold spectacles worn low on his nose. His signature is a spectacular authentic ginger hairstyle shaped into two tall vertical symmetrical rounded columns above each temple, smooth shaved central part, and a thin straight pencil moustache. Hair is visibly made of real hair, meticulously groomed, physically plausible but outrageously unfashionable. He wears a fitted olive-green velvet three-piece suit, a cream shirt with enormous pointed 1970s collar, burgundy necktie. Perfectly serious lips, mild self-important eye contact. Hands relaxed, no held props. The funny unsettling effect must come entirely from his unforgettable silhouette, very specific face and completely sincere formal bearing in ordinary life. Human anatomy and real textured skin, believable wrinkles and velvet nap, natural cloudy daylight, slightly imperfect amateur phone framing. Feels like an unexpected real person found on the feed, not a fashion campaign, not a horror character or cartoon. No typography, no logos, no fantasy anomalies. Do not use a blond pageboy haircut.",
      "model_name": "GPT Image 2.5",
      "model_id": "gpt-image-2-5",
      "duration_s": "",
      "resolution": "2k",
      "aspect_ratio": "9:16",
      "settings": "Made September 30, 2026; Text to image, no reference; Aspect ratio 9:16; Quality high; Resolution 2k; Variant sunburst",
      "studio_settings": "aspectRatio=9:16; quality=high; resolution=2k; variant=sunburst",
      "credits": 20,
      "media_url": "https://twistavo.com/prompts/recurring-ai-character-cast/claude-portrait.webp",
      "media_kind": "image",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/recurring-ai-character-cast",
      "example_id": "brigitte-portrait",
      "example_title": "BRIGITTE is born: the same recipe in a cafe (GPT Image 2.5)",
      "prompt": "ONE photoreal portrait of an entirely original fictional eccentric social-media character, waist-up vertical casual phone snapshot in an ordinary French cafe. Mireille, a very tall slender woman aged 48 with a long narrow face, prominent cheekbones, wide-set hazel eyes, sparse straight brows, long nose and tightly pursed lipstick-red lips. Her sculptural copper-red hair is rolled into one enormous perfectly round smooth vertical coil centered high above her head, like an oversized polished cinnamon-roll silhouette made only of real hair, with tiny tightly curled side locks at her ears. Small circular cobalt-blue spectacles. High-neck cream blouse with a large scalloped collar, cobalt-blue fitted jacket and matching blue fabric-covered buttons. Her fixed solemn gaze and formal upright posture make her seem completely unaware of how extraordinary she looks. Empty hands resting naturally at waist. The character herself is the hook: elegant, strange, immediately recognizable, human and slightly awkward rather than glamorous. Mundane cafe furniture behind her, authentic skin texture and flyaway hairs, flat window daylight, ordinary imperfect phone-photo realism. No cinematic grading, no horror, no supernatural reflection, no caption, no logo, no watermark. No blond pageboy hairstyle, no copying existing people.",
      "model_name": "GPT Image 2.5",
      "model_id": "gpt-image-2-5",
      "duration_s": "",
      "resolution": "2k",
      "aspect_ratio": "9:16",
      "settings": "Made September 30, 2026; Text to image, no reference; Aspect ratio 9:16; Quality high; Resolution 2k; Variant sunburst",
      "studio_settings": "aspectRatio=9:16; quality=high; resolution=2k; variant=sunburst",
      "credits": 20,
      "media_url": "https://twistavo.com/prompts/recurring-ai-character-cast/brigitte-portrait.webp",
      "media_kind": "image",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/recurring-ai-character-cast",
      "example_id": "claude-sheet",
      "example_title": "From portrait to 3-view sheet (Seedream 5.0 Pro)",
      "prompt": "A soft, low-contrast film character sheet with quiet, delicate texture: the entire image lives in a broad, gentle middle register — highlights roll off early into soft cream while keeping full detail, shadows sit lifted, open and airy, micro-contrast stays low and tender, skin and fabric resolve with smooth, quiet, organic detail, edges stay rounded and creamy under a gentle veil of optical diffusion, as through an old uncoated vintage cinema prime, with a soft halation bloom breathing from the brightest points — the whole sheet reading like a delicately printed film photograph with a modern neutral colour grade.\n\nWithin that look, and using the attached image strictly as the identity reference for the person — their face, age, build, hair and costume are canon and must match the reference 100% — generate the character sheet: three stills of this same person arranged side by side on one sheet: FULL-BODY FRONT view on the left, FULL-BODY BACK view in the middle, and a THREE-QUARTER portrait on the right. The same person, identical outfit and proportions across all three panels, standing on a seamless PURE WHITE studio background that keeps its own even, luminous brightness, reading as clean paper; full figure in frame head to shoes with clear space above the head and below the feet, a soft contact shadow grounding them. Carry over only the person themselves: they stand alone in clean, empty white studio space, lifted out of the reference's scene and simply relit.\n\nThe character, anchored to the reference: exactly the person in the attached image, at their exact age and build, with their exact face carried over one-to-one as photographed — the precise hairline and haircut, the natural asymmetry between the left and right halves of the face, the true set of the eyes, nose and mouth, every crease, mark, shadow and skin texture kept as in the reference, real skin softly resolved — the same lived-in cinematic face, simply relit. They wear their reference costume exactly: every garment, its colours, closures, layers, accessories, folds and wear marks carried over consistent with the reference. Below the reference's frame edge the costume is completed faithfully in the same style, period and quality as the visible garments, down to period-true footwear. They stand NEUTRALLY with empty, relaxed hands: weight even on both feet, arms at their sides, shoulders level, head straight; expression neutral and at rest, mouth closed, face calm, eyes open and readable with soft catchlights.\n\nFRONT panel: facing camera square, the costume's front reading clearly — its closures, collar, accessories and colours exactly as in the reference. BACK panel: turned fully away — the haircut from behind, the costume's back completed faithfully in the same period and construction, the sleeves at their sides, the trouser or hem line, the heels of the footwear. THREE-QUARTER portrait panel: a CHEST-LEVEL close portrait — the frame runs from just above the top of the head down to the upper chest, the bottom edge cutting across the chest, so the head and face fill most of the panel; face turned three-quarters to camera, calm and still, with the reference's exact asymmetry and every facial feature carried over unchanged — hairline, creases, skin and all.\n\nThe light is neutral and even across all three panels — a soft ambient wash, as if the whole space sits under a broad overcast sky: directionless, calm, arriving frontal and even, wrapping the figure gently, open transparent shadows, every fabric reading true, the exposure holding the low-contrast filmic register declared above. The figure's outline meets the pure white background softly along every edge. The colour story comes from the reference itself: the costume's dominant colour as the leading mass against the pure white field, its secondary tones as the supporting masses, and the smallest bright detail of the reference costume as the single accent.\n\nWardrobe completion: complete Claude Frangeçois's outfit with full-length straight olive-green velvet tailored trousers matching the visible jacket, and polished dark-brown leather Oxford shoes. Keep these trousers and shoes identical in the front and back panels.",
      "model_name": "Seedream 5.0 Pro",
      "model_id": "seedream-v5-pro",
      "duration_s": "",
      "resolution": "2k",
      "aspect_ratio": "16:9",
      "settings": "Made September 30, 2026; Image to image, 1 reference image (the portrait above); Aspect ratio 16:9; Resolution 2k",
      "studio_settings": "aspectRatio=16:9; resolution=2k",
      "credits": 22,
      "media_url": "https://twistavo.com/prompts/recurring-ai-character-cast/claude-sheet.webp",
      "media_kind": "image",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/recurring-ai-character-cast",
      "example_id": "brigitte-sheet",
      "example_title": "Same template, second character (Seedream 5.0 Pro)",
      "prompt": "A soft, low-contrast film character sheet with quiet, delicate texture: the entire image lives in a broad, gentle middle register — highlights roll off early into soft cream while keeping full detail, shadows sit lifted, open and airy, micro-contrast stays low and tender, skin and fabric resolve with smooth, quiet, organic detail, edges stay rounded and creamy under a gentle veil of optical diffusion, as through an old uncoated vintage cinema prime, with a soft halation bloom breathing from the brightest points — the whole sheet reading like a delicately printed film photograph with a modern neutral colour grade.\n\nWithin that look, and using the attached image strictly as the identity reference for the person — their face, age, build, hair and costume are canon and must match the reference 100% — generate the character sheet: three stills of this same person arranged side by side on one sheet: FULL-BODY FRONT view on the left, FULL-BODY BACK view in the middle, and a THREE-QUARTER portrait on the right. The same person, identical outfit and proportions across all three panels, standing on a seamless PURE WHITE studio background that keeps its own even, luminous brightness, reading as clean paper; full figure in frame head to shoes with clear space above the head and below the feet, a soft contact shadow grounding them. Carry over only the person themselves: they stand alone in clean, empty white studio space, lifted out of the reference's scene and simply relit.\n\nThe character, anchored to the reference: exactly the person in the attached image, at their exact age and build, with their exact face carried over one-to-one as photographed — the precise hairline and haircut, the natural asymmetry between the left and right halves of the face, the true set of the eyes, nose and mouth, every crease, mark, shadow and skin texture kept as in the reference, real skin softly resolved — the same lived-in cinematic face, simply relit. They wear their reference costume exactly: every garment, its colours, closures, layers, accessories, folds and wear marks carried over consistent with the reference. Below the reference's frame edge the costume is completed faithfully in the same style, period and quality as the visible garments, down to period-true footwear. They stand NEUTRALLY with empty, relaxed hands: weight even on both feet, arms at their sides, shoulders level, head straight; expression neutral and at rest, mouth closed, face calm, eyes open and readable with soft catchlights.\n\nFRONT panel: facing camera square, the costume's front reading clearly — its closures, collar, accessories and colours exactly as in the reference. BACK panel: turned fully away — the haircut from behind, the costume's back completed faithfully in the same period and construction, the sleeves at their sides, the trouser or hem line, the heels of the footwear. THREE-QUARTER portrait panel: a CHEST-LEVEL close portrait — the frame runs from just above the top of the head down to the upper chest, the bottom edge cutting across the chest, so the head and face fill most of the panel; face turned three-quarters to camera, calm and still, with the reference's exact asymmetry and every facial feature carried over unchanged — hairline, creases, skin and all.\n\nThe light is neutral and even across all three panels — a soft ambient wash, as if the whole space sits under a broad overcast sky: directionless, calm, arriving frontal and even, wrapping the figure gently, open transparent shadows, every fabric reading true, the exposure holding the low-contrast filmic register declared above. The figure's outline meets the pure white background softly along every edge. The colour story comes from the reference itself: the costume's dominant colour as the leading mass against the pure white field, its secondary tones as the supporting masses, and the smallest bright detail of the reference costume as the single accent.\n\nWardrobe completion: complete Mireille Bigoudi's outfit with high-waisted cobalt-blue tailored flared trousers matching the visible jacket, and black leather ankle boots with a low sculpted heel. Keep these trousers and boots identical in the front and back panels.",
      "model_name": "Seedream 5.0 Pro",
      "model_id": "seedream-v5-pro",
      "duration_s": "",
      "resolution": "2k",
      "aspect_ratio": "16:9",
      "settings": "Made September 30, 2026; Image to image, 1 reference image (the portrait above); Aspect ratio 16:9; Resolution 2k",
      "studio_settings": "aspectRatio=16:9; resolution=2k",
      "credits": 22,
      "media_url": "https://twistavo.com/prompts/recurring-ai-character-cast/brigitte-sheet.webp",
      "media_kind": "image",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/recurring-ai-character-cast",
      "example_id": "head-walrus-moustache",
      "example_title": "New head on the same body: blond bob and walrus moustache (Nano Banana 2 Lite)",
      "prompt": "Use image_0.png as identity and composition reference for a faithful image-to-image edit. Keep the body, the brown checked tweed suit, white shirt, tie, pose, framing, background and lighting exactly the same. Replace ONLY the head and hair with this new design: a strong square face with a prominent chin, thick dark-brown walrus mustache in sharp contrast with the neat blunt blond bob, bushy expressive eyebrows, small sharp hazel eyes with a confident squint, weathered tanned skin, faint smirk of absolute self-satisfaction. A tiny braggart champion energy. 100% a real believable human. Ultra-photorealistic skin with visible pores, mustache hairs and natural asymmetry, looks like a real photograph, not CGI, not a caricature drawing. Same neutral lighting and photo style. No text, no labels, no watermark.",
      "model_name": "Nano Banana 2 Lite",
      "model_id": "nano-banana-2-lite",
      "duration_s": "",
      "resolution": "",
      "aspect_ratio": "auto",
      "settings": "Made September 30, 2026; Image to image, 1 reference image (the CLAUDE sheet above); Aspect ratio auto (16:9 output); Thinking high; Resolution 1k",
      "studio_settings": "aspectRatio=auto; thinking=HIGH",
      "credits": 9,
      "media_url": "https://twistavo.com/prompts/recurring-ai-character-cast/head-walrus-moustache.webp",
      "media_kind": "image",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/recurring-ai-character-cast",
      "example_id": "head-gaunt-fringe",
      "example_title": "Failure: the head changed, and so did the suit (Nano Banana 2 Lite)",
      "prompt": "Use image_0.png as identity and composition reference for a faithful image-to-image edit. Keep the body, the brown checked tweed suit, white shirt, tie, pose, framing, background and lighting exactly the same. Replace ONLY the head and hair with this new design: a long narrow aristocratic face — sharp cheekbones, pronounced brow, large straight nose, thin disapproving mouth, strong jaw, deep-set pale grey eyes with heavy dark circles and a tired contemptuous stare, light freckles, short messy strawberry-blond hair with a blunt fringe. A gaunt exhausted nobleman who has seen everything. 100% a real believable human. Ultra-photorealistic skin with visible pores, subtle veins and natural asymmetry, looks like a real photograph, not CGI, not a caricature drawing. Same neutral lighting and photo style. No text, no labels, no watermark.",
      "model_name": "Nano Banana 2 Lite",
      "model_id": "nano-banana-2-lite",
      "duration_s": "",
      "resolution": "",
      "aspect_ratio": "auto",
      "settings": "Made September 30, 2026; Image to image, 1 reference image (the CLAUDE sheet above); Aspect ratio auto (16:9 output); Thinking high; Resolution 1k",
      "studio_settings": "aspectRatio=auto; thinking=HIGH",
      "credits": 9,
      "media_url": "https://twistavo.com/prompts/recurring-ai-character-cast/head-gaunt-fringe.webp",
      "media_kind": "image",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/recurring-ai-character-cast",
      "example_id": "head-grandmother",
      "example_title": "New head: an elderly woman's face on the suited body (Nano Banana 2 Lite)",
      "prompt": "Use image_0.png as identity and composition reference for a faithful image-to-image edit. Keep the body, brown checked tweed suit, white shirt, tie, pose, framing, background and lighting exactly the same. Replace ONLY the head and hair with this design: the kind, warm face of a plump elderly grandmother on this suited man's body — soft round wrinkled cheeks, gentle laughing crow's feet, small kind eyes behind tiny oval gold-rimmed glasses, silver-grey permed hair set neatly, small pearl earrings, a faint benign smile. The face reads clearly as a sweet grandma in her seventies while the body is the adult man's tailored tweed suit. Uncanny, tender and absurd. 100% photorealistic: believable aged skin, visible pores and wrinkles, natural asymmetry, looks like a real photograph, not CGI, not a mask, not horror. Same neutral lighting and photo style. No text, no labels, no watermark.",
      "model_name": "Nano Banana 2 Lite",
      "model_id": "nano-banana-2-lite",
      "duration_s": "",
      "resolution": "",
      "aspect_ratio": "auto",
      "settings": "Made September 30, 2026; Image to image, 1 reference image (the CLAUDE sheet above); Aspect ratio auto (16:9 output); Thinking high; Resolution 1k",
      "studio_settings": "aspectRatio=auto; thinking=HIGH",
      "credits": 9,
      "media_url": "https://twistavo.com/prompts/recurring-ai-character-cast/head-grandmother.webp",
      "media_kind": "image",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/seedance-2-5-character-sheet-to-video",
      "example_id": "restaurant-cloche",
      "example_title": "Restaurant: the cloche and the single crumb",
      "prompt": "An ORIGINAL live-action-style physical comedy, not a recreation of any film. @Image1 is a character sheet showing multiple views of ONE pigeon; @Image2 shows multiple views of ONE hammerhead shark. Only TWO main characters, never duplicate the reference panels. Keep their identities constant: the pigeon has slate feathers, orange eyes, an iridescent teal-purple neck, plain navy zipped hoodie and trousers with white sneakers. The taller, broad hammerhead has blue-grey skin, ivory throat, dark navy polo, charcoal trousers and black shoes. Reference pictures control identity and clothes ONLY, not poses, expressions, backdrop or shot order. They behave like serious ordinary adults; the situation is funny but their world treats them as normal. Photorealistic integrated bodies, realistic scale, contact shadows and natural anatomy. Vertical phone-native composition, medium and medium-wide framing with readable faces and props. No split screen, captions, letters, logos, branded objects or watermarks. Native environmental audio, synchronized footsteps and object sounds, short natural amused breaths only; no spoken dialogue, no narrator, no music, no canned laugh track. Allow the actions to breathe, do not use a montage. At an elegant but unbranded restaurant table, the hammerhead solemnly presents an enormous covered serving plate to the seated pigeon like a fine-dining waiter. He slowly lifts the silver cloche, revealing just ONE small breadcrumb in the centre of the huge white plate. Instead of disappointment, the pigeon is visibly delighted: he straightens, carefully inspects the crumb, picks it delicately with his beak and savours it like a gourmet. The shark then produces an equally enormous second cloche from the nearby trolley. The pigeon lights up with anticipation. Finish before the second reveal for a natural loop. No bill, printed menu, text or spoken words.",
      "model_name": "Seedance 2.5",
      "model_id": "seedance-2.5",
      "duration_s": "15",
      "resolution": "720p",
      "aspect_ratio": "9:16",
      "settings": "Made September 29, 2026; Reference to video, 2 reference images (the two character sheets); Aspect ratio 9:16; Duration 15 s; Resolution 720p; Audio on (model-generated, removed here)",
      "studio_settings": "aspectRatio=9:16; duration=15; resolution=720p; generateAudio=true; bitrateMode=standard",
      "credits": 901,
      "media_url": "https://twistavo.com/prompts/seedance-2-5-character-sheet-to-video/restaurant-cloche.mp4",
      "media_kind": "video",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/seedance-2-5-character-sheet-to-video",
      "example_id": "diner-fry",
      "example_title": "Failure: the diner fry without the look away",
      "prompt": "An ORIGINAL live-action-style physical comedy, not a recreation of any film. @Image1 is a character sheet showing multiple views of ONE pigeon; @Image2 shows multiple views of ONE hammerhead shark. Only TWO main characters, never duplicate the reference panels. Keep their identities constant: the pigeon has slate feathers, orange eyes, an iridescent teal-purple neck, plain navy zipped hoodie and trousers with white sneakers. The taller, broad hammerhead has blue-grey skin, ivory throat, dark navy polo, charcoal trousers and black shoes. Reference pictures control identity and clothes ONLY, not poses, expressions, backdrop or shot order. They behave like serious ordinary adults; the situation is funny but their world treats them as normal. Photorealistic integrated bodies, realistic scale, contact shadows and natural anatomy. Vertical phone-native composition, medium and medium-wide framing with readable faces and props. No split screen, captions, letters, logos, branded objects or watermarks. Native environmental audio, synchronized footsteps and object sounds, short natural amused breaths only; no spoken dialogue, no narrator, no music, no canned laugh track. Allow the actions to breathe, do not use a montage. At a small diner booth, the pigeon and the hammerhead sit facing each other with one last golden french fry clearly visible on a white plate between them. Both keep a straight face. For the first five seconds each slowly reaches toward it, then politely withdraws when the other moves. In seconds 5-10 the shark looks away for a split second; the pigeon snaps up the fry once with his beak, quick but clearly readable. In seconds 10-15 the shark looks back at the empty plate. The pigeon innocently folds his hands, while a tiny end of the fry still sticks out of his beak. The shark points at that telltale end. Hold on the caught-out guilty look. No food teleporting or changing plates.",
      "model_name": "Seedance 2.5",
      "model_id": "seedance-2.5",
      "duration_s": "15",
      "resolution": "720p",
      "aspect_ratio": "9:16",
      "settings": "Made September 29, 2026; Reference to video, 2 reference images (the two character sheets); Aspect ratio 9:16; Duration 15 s; Resolution 720p; Audio on (model-generated, removed here)",
      "studio_settings": "aspectRatio=9:16; duration=15; resolution=720p; generateAudio=true; bitrateMode=standard",
      "credits": 901,
      "media_url": "https://twistavo.com/prompts/seedance-2-5-character-sheet-to-video/diner-fry.mp4",
      "media_kind": "video",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/seedance-2-5-character-sheet-to-video",
      "example_id": "security-gate",
      "example_title": "Failure: the shark never gets through the gate (480p)",
      "prompt": "An ORIGINAL live-action-style physical comedy, not a recreation of any film. @Image1 is a character sheet showing multiple views of ONE pigeon; @Image2 shows multiple views of ONE hammerhead shark. Only TWO main characters, never duplicate the reference panels. Keep their identities constant: the pigeon has slate feathers, orange eyes, an iridescent teal-purple neck, plain navy zipped hoodie and trousers with white sneakers. The taller, broad hammerhead has blue-grey skin, ivory throat, dark navy polo, charcoal trousers and black shoes. Reference pictures control identity and clothes ONLY, not poses, expressions, backdrop or shot order. They behave like serious ordinary adults; the situation is funny but their world treats them as normal. Photorealistic integrated bodies, realistic scale, contact shadows and natural anatomy. Vertical phone-native composition, medium and medium-wide framing with readable faces and props. No split screen, captions, letters, logos, branded objects or watermarks. Native environmental audio, synchronized footsteps and object sounds, short natural amused breaths only; no spoken dialogue, no narrator, no music, no canned laugh track. Allow the actions to breathe, do not use a montage. In a quiet office lobby, the pigeon walks easily through an open waist-high entrance turnstile. The hammerhead follows, but his wide head will not fit between two upright padded guide panels at shoulder height. 0-4s establish the pigeon passing and the shark stopping with his head gently touching both padded sides, no injury. 4-8s the shark tries leaning but his horizontal head is still too wide; the pigeon notices and silently points sideways. 8-12s the shark turns his whole body exactly ninety degrees, his thin head profile now passes cleanly between the panels, and he steps through sideways. 12-15s the shark straightens proudly; the pigeon gives one deadpan approving nod, then looks straight at the camera. The comic solution must be clearly shown, with stable head geometry and actual passage through the gap. No head shrinking, morphing, teleportation or extra gate.",
      "model_name": "Seedance 2.5",
      "model_id": "seedance-2.5",
      "duration_s": "15",
      "resolution": "480p",
      "aspect_ratio": "9:16",
      "settings": "Made September 29, 2026; Reference to video, 2 reference images (the two character sheets); Aspect ratio 9:16; Duration 15 s; Resolution 480p; Audio on (model-generated, removed here)",
      "studio_settings": "aspectRatio=9:16; duration=15; resolution=480p; generateAudio=true; bitrateMode=standard",
      "credits": 386,
      "media_url": "https://twistavo.com/prompts/seedance-2-5-character-sheet-to-video/security-gate.mp4",
      "media_kind": "video",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/seedance-2-5-found-footage-prompts",
      "example_id": "whale-over-cafe",
      "example_title": "A sperm whale glides over a seaside cafe terrace (15 s)",
      "prompt": "An impossibly enormous sperm whale glides through open air just above an ordinary Mediterranean seaside cafe terrace in daylight. Its square head and long charcoal-grey body are already visibly suspended above the umbrellas at the opening. Adult customers, tables and the stone buildings behind them make its overwhelming scale unmistakable: the whale is as long as two city buses. It is one solid, anatomically convincing animal, not a shape made of clouds.\n\nRender the entire scene as extremely realistic, ungraded live-action: wrinkled whale skin with subtle natural imperfections, ordinary weathered facades, woven cafe chairs, canvas umbrellas and ceramic cups. Low afternoon sunlight illuminates the animal and the terrace from the same direction. Its broad shadow travels across the paving, tables and people as its body passes overhead. Flying is the only impossible thing; the surroundings retain their everyday material behavior.\n\nStage one continuous, readable passage from left to right across the open plaza. Keep the whale clearly separated from rooftops, umbrellas and people. Observe from terrace level with enough width to retain customers and architecture as scale references; a restrained upward reframe follows the animal without hiding its body or turning the scene into a montage. The customers interrupt their ordinary actions at different moments: a cup stops halfway to a mouth, two heads turn upward, one person slowly rises from a chair. Subtle reactions, not synchronized theatrical screaming. Umbrella fabric stirs gently. The heavy torso passes, followed by a slow natural movement of the tail flukes. End after the tail clears the terrace and sunlight returns to the tables, with the customers still staring after it. Preserve the same whale, people and location throughout.\n\nNative sound: cafe ambience, a ceramic cup touching its saucer, wind through umbrella fabric, quiet surprised breaths and a deep organic rumble during the passage. No music, narration or scripted dialogue. No written text, logo, watermark, fantasy glow, cartoon styling or glossy video-game surfaces.",
      "model_name": "Seedance 2.5",
      "model_id": "seedance-2.5",
      "duration_s": "15",
      "resolution": "480p",
      "aspect_ratio": "9:16",
      "settings": "Text to video, no reference; Aspect ratio 9:16; Duration 15 s; Resolution 480p; Audio on; Bitrate standard",
      "studio_settings": "aspectRatio=9:16; duration=15; resolution=480p; generateAudio=true; bitrateMode=standard",
      "credits": 386,
      "media_url": "https://twistavo.com/prompts/seedance-2-5-found-footage-prompts/whale-over-cafe.mp4",
      "media_kind": "video",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/seedance-2-5-found-footage-prompts",
      "example_id": "4d-cinema-wave",
      "example_title": "A 4D cinema screen spills a wave into the aisle (12 s)",
      "prompt": "Original fictional 4D cinema video, photorealistic and shot like a surprised adult audience member recording vertically from the middle row. Viewer IS the recording camera: no phone, screen-in-a-phone, filming hand, selfie stick or rig inside the image. Normal red cinema seats with a handful of adult patrons, aisle and a huge wall-to-wall projection screen visible. Natural imperfect handheld movement and sensible exposure. One continuous readable event, never a trailer montage. Keep theatre architecture and audience positions coherent. No real film footage, celebrities, licensed characters, writing, logos, subtitles or watermark. Native room tone, mechanical seat sounds, startled gasps and precisely synchronized environmental effects. No music and no spoken narration. All people remain safe; this is a playful impossible cinema illusion, not an actual disaster. The projection shows a sunlit empty tropical shoreline, with a modest turquoise wave approaching the camera inside the projected scene. 0-3s the sea looks almost convincingly connected to the aisle. 3-7s a shallow sheet of turquoise water spills smoothly out from the BOTTOM EDGE of the projection and flows gently along the theatre aisle; keep its height below the soles of the seats, never flooding or submerging anyone. Two nearby patrons lift their feet, laughing with surprise. 7-10s a little rubber duck floats down the aisle and bumps gently against the front seat. 10-12s one patron lifts their 3D glasses, looks at the duck, then toward the recording camera in disbelief. The theatre never becomes an outdoor beach. The water-screen boundary and the duck are both readable. The reveal is delightful and absurd, no destruction, panic, screaming or injury.",
      "model_name": "Seedance 2.5",
      "model_id": "seedance-2.5",
      "duration_s": "12",
      "resolution": "480p",
      "aspect_ratio": "9:16",
      "settings": "Text to video, no reference; Aspect ratio 9:16; Duration 12 s; Resolution 480p; Audio on; Bitrate standard",
      "studio_settings": "aspectRatio=9:16; duration=12; resolution=480p; generateAudio=true; bitrateMode=standard",
      "credits": 309,
      "media_url": "https://twistavo.com/prompts/seedance-2-5-found-footage-prompts/4d-cinema-wave.mp4",
      "media_kind": "video",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/seedance-2-5-found-footage-prompts",
      "example_id": "kayak-cup-roll",
      "example_title": "A kayaker rolls under water holding a full cup (10 s)",
      "prompt": "Raw vertical smartphone witness video filmed from knee-deep crystal-clear turquoise water beside a quiet rocky cove in daylight. An ordinary adult kayaker sits in a narrow recreational kayak only a few metres from the phone, already holding a completely full transparent plastic cup high above one shoulder so the challenge is understood immediately. Friends nearby laugh and gasp. The kayaker slowly leans sideways, the kayak rolls fully upside down and the person disappears under the water while the raised arm fights to keep the cup upright above the surface. Hold the suspense naturally for a moment. Then the kayaker completes the roll and resurfaces upright, soaked and laughing, still holding the visibly full cup without spilling. One believable continuous handheld phone take at water level, imperfect framing, natural autofocus and exposure, real water resistance and splashes, no cuts, no slow motion, no polished commercial look. Native synchronized water splashes, paddle and kayak creaks, surprised laughter and cheering only; no narration, no music. No text, no subtitles, no logo, no brand, no extra limbs, no duplicated people, no impossible morphing. End directly on the successful reveal and genuine reaction.",
      "model_name": "Seedance 2.5",
      "model_id": "seedance-2.5",
      "duration_s": "10",
      "resolution": "720p",
      "aspect_ratio": "9:16",
      "settings": "Text to video, no reference; Aspect ratio 9:16; Duration 10 s; Resolution 720p; Audio on; Bitrate high",
      "studio_settings": "aspectRatio=9:16; duration=10; resolution=720p; generateAudio=true; bitrateMode=high",
      "credits": 601,
      "media_url": "https://twistavo.com/prompts/seedance-2-5-found-footage-prompts/kayak-cup-roll.mp4",
      "media_kind": "video",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/storyboard-sheet",
      "example_id": "shed-4x4",
      "example_title": "4x4 grid with one homeowner across 16 panels (GPT Image 2)",
      "prompt": "Storyboard 4x4 grid, 16 distinct panels, for a short vertical social video about a homeowner who has ordered a small wooden garden shed. Concrete story: panel progression shows the boxed shed arriving, a tape measure and boundary fence, a proposed placement too close to the property line, the homeowner pausing before digging, a clean abstract planning check with no readable UI or invented text, the project moved inward, relieved but matter-of-fact homeowner, final view of shed safely placed with open space for CTA. Photorealistic French suburban garden, consistent one homeowner, natural daylight, documentary social-video visual language. No logos, no captions, no readable text, no fake interface, no legal claims. The sheet is only a visual storyboard, not final footage.",
      "model_name": "GPT Image 2",
      "model_id": "gpt-image-2",
      "duration_s": "",
      "resolution": "2k",
      "aspect_ratio": "3:2",
      "settings": "GPT Image 2, text to image; Aspect ratio 3:2; Quality high; Resolution 2k",
      "studio_settings": "aspectRatio=3:2; quality=high; resolution=2k",
      "credits": 61,
      "media_url": "https://twistavo.com/prompts/storyboard-sheet/shed-4x4.webp",
      "media_kind": "image",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/storyboard-sheet",
      "example_id": "fruit-market-3x2",
      "example_title": "3x2 grid with three fruit characters (Seedream 5.0 Pro)",
      "prompt": "Create ONE production storyboard CONTACT SHEET made of SIX genuine high-end photorealistic cinematic 3D still images, NOT sketches, NOT vector art, NOT diagrams. Exactly six equal distinct panels in a strict 3-column by 2-row grid, left-to-right top row then left-to-right across the bottom row, thin straight dark gutters and nothing else. Each individual panel is composed like a vertical 9:16 smartphone film still. No decorative border, no header, no panel numbers, no captions, no speech bubbles, no subtitles, no Arabic or English words, no logos or watermark. All written sticker/phone text will be overlaid later. This sheet will be cropped into six separate shot images. All characters are original, non-franchise.\n\nCHARACTER AND LOCATION LOCK: Inside a fantastical North African produce market with warm overhead bulbs, wooden fruit crates and a red-and-cream striped awning, show the same three original fruit characters in every frame where present: DELLA3A is a round dark-green striped watermelon with a small green curled leaf on top, large dark-brown eyes and a distinctive little notch in the rind under her left eye, short realistic fruit-textured arms. LIMOUNA is a smaller bright yellow lemon with pointed ends, freckles on the peel, narrow dark eyes, sharply arched expressive brows and small peel-textured arms. TAMRA is a chestnut-brown date with one small green stem, two gentle wide-set hazel eyes and slim brown arms. Faces integrated naturally into fruit surfaces, tactile peel textures, expressive physical acting, same sizes/markings/colors in all panels. Tangible high-end cinematic 3D, not flat cartoon graphics. Same market geography and amber lighting throughout except the deliberately desaturated security-camera view in panel four. No other speaking fruit.\n\nSTORY BEATS, ONE CLEAR PHOTOGRAPHIC SHOT PER PANEL:\n1. CLOSE-UP: Della3a discovers a rectangular RED sticker with a THIN WHITE border already pressed against her striped rind. Her mouth is open in shocked indignation. The sticker is BLANK, without any written letters; later overlay will read 'فاسدة'.\n2. REVERSE ANGLE: Limouna publicly points at Della3a in accusation in front of the market crates; Della3a recoils in the background. Tamra is a small silent witness. Red sticker still attached to Della3a.\n3. MEDIUM SHOT: Tamra holds a smartphone outward toward both fruits and the camera; a paused security-camera view on its screen shows yellow Limouna near green Della3a. Screen has no readable text or numbers. Della3a looks shocked; Limouna looks nervous.\n4. SECURITY CAMERA INSERT: desaturated overhead camera viewpoint of the SAME market and SAME three-dimensional characters. It unmistakably shows Limouna pressing the SAME rectangular red white-edged blank sticker directly onto Della3a's rind with her small hand. No text, no timestamp. The sticker is in physical contact with the green rind.\n5. TWO-SHOT CONFRONTATION: Della3a and Limouna face one another closely, the red sticker still on Della3a. Tamra stands behind them holding the phone. Della3a demands an explanation; Limouna's accusatory confidence has disappeared.\n6. CLIFFHANGER: in the SAME market, frightened Limouna whispers toward Della3a beside ONE large sealed cardboard fruit box. The box bulges very slightly under its closed lid, suggesting something moving inside. Do not open it, show its contents, introduce a fourth fruit, or reveal the second watermelon yet.\n\nThe six frames must depict the same DELLA3A, LIMOUNA and TAMRA identities with consistent physical markings and outfits (no clothing). Each panel tells exactly one beat, continuous red sticker placement, no swapped fruit identities, no extra panels or duplicated frames. Photoreal textured materials, dramatic but believable market light and expressive cinematic framing. Spoken Algerian Darija, all on-screen text, subtitle lettering and sound effects will be added separately in editing.",
      "model_name": "Seedream 5.0 Pro",
      "model_id": "seedream-v5-pro",
      "duration_s": "",
      "resolution": "2k",
      "aspect_ratio": "3:4",
      "settings": "Seedream 5.0 Pro, text to image; Aspect ratio 3:4; Resolution 2k",
      "studio_settings": "aspectRatio=3:4; resolution=2k",
      "credits": 22,
      "media_url": "https://twistavo.com/prompts/storyboard-sheet/fruit-market-3x2.webp",
      "media_kind": "image",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/storyboard-sheet",
      "example_id": "pompeii-4x4",
      "example_title": "Vertical 4x4 grid of a miniature disaster scene (GPT Image 2.5)",
      "prompt": "UNE PLANCHE DE STORYBOARD PHOTOGRAPHIQUE : EXACTEMENT SEIZE CASES, QUATRE COLONNES et QUATRE RANGÉES régulières, lecture gauche-droite puis haut-bas. Chaque case contient une seule photographie verticale9:16. Ensemble vertical9:16. Trois fines gouttières blanches verticales et trois horizontales continues, droites et uniformes. Pas de case fusionnée, de cinquième rangée ou de collage libre. Aucun texte, chiffre, légende, bulle, logo, marque, watermark ou signature DANS les images. Les titres ci-dessous ne doivent pas être dessinés.\n\nHISTOIRE — POMPÉI, UNE CATASTROPHE MINIATURE FILMÉE EN STUDIO\nUn marché romain vivant est bouleversé par une secousse. Le Vésuve entre en éruption; une nuée ardente descend vers la ville, frappe les bâtiments et envahit la place. Après son passage, la même ville reste détruite et ensevelie sous les cendres. L'histoire doit être compréhensible même si l'on ignore l'équipe technique. La scène filmée est le héros; le making-of fournit le contexte et les repères de taille. C'est une interprétation de cinéma condensée, pas une reconstruction scientifique ou une carte archéologique.\n\nÉCHELLE ABSOLUE À CONSERVER\nLes techniciens modernes sont des ADULTES DE TAILLE NORMALE. La cité, ses habitants et le volcan sont un PETIT MONDE à échelle réduite. Un Romain entier est plus petit que la main d'un technicien. Les toits sont beaucoup plus bas que la taille des vrais opérateurs. Le volcan lui-même appartient au décor réduit : son sommet solide reste sous leurs épaules. Il ne devient jamais une vraie montagne occupant tout le hangar. Son panache peut dépasser le petit cône, mais une grande hauteur de studio reste dégagée au-dessus. Ne pas réduire les techniciens pour agrandir la ville; ne pas rendre les Romains grandeur nature. L'importance narrative du décor ne change pas sa taille.\nUne maquette de plateau riche et dense, construite AU SOL sur une grande zone de tournage, pas un petit jouet dans une boîte sur table. Adultes romains minuscules et réalistes en poses vivantes, pas soldats en plastique ni enfants. Pas de ville moderne ni gratte-ciel. Tous les états de destruction conservent ces proportions.\n\nCAMÉRA ET STUDIO\nPhotographies prises par caméra observatrice B depuis derrière une petite équipe moderne et caméra de cinéma A. B reste extérieure au petit monde, à hauteur humaine légèrement surélevée, même côté et même axe dans les SEIZE cases. Cadrage large à moyen-large stable : le décor central est lisible, avec de vrais techniciens/caméra en amorce basse et latérale, et le haut hangar visible. Aucun plan pris au milieu des Romains; aucun gros plan qui efface les repères de miniature. Pas d'insertion en extérieur et pas de faux cadre de moniteur.\nPremier plan : trois ou quatre vrais techniciens modernes en noir/gris, caméra A sur dolly, rails et câbles normaux, hors du petit décor. Deuxième profondeur : Pompéi miniature et son Vésuve sur le même plateau. Troisième : immense hangar, charpente très haute, passerelles, projecteurs suspendus, cyclorama bleu lointain. Équipe en périphérie, jamais un mur de dos cachant la place. Deux silhouettes partielles et caméra suffisent après l'établissement. La nuée touche la maquette, pas les personnes réelles ni les poutres du studio. Les réactions du crew restent secondaires.\n\nGÉOGRAPHIE ET OBJETS FIXES\nMême ville romaine méditerranéenne dans toutes les cases : forum rectangulaire au premier plan du set, petite FONTAINE RONDE au milieu, MARCHÉ à AUVENT ROUGE à gauche, TEMPLE CLAIR à colonnes à droite. Maisons de stuc ocre, toits de tuiles terre cuite et pavés. Une rue centrale mène au Vésuve miniature à l'arrière. Marchande adulte à étoffe ocre, client adulte en tunique bleue, porteur et autres passants adultes en tuniques écrues. Une petite charrette de bois chargée d'amphores près de la fontaine. Aucun costume moderne dans la cité, aucun technicien au milieu des petits habitants. Pas de personnages géants.\nLe flux destructeur a UNE ORIGINE et UNE DIRECTION : cratère au fond, pente, maisons arrière, rue, forum avant. Au début, le marché est intact et vivant. Puis amphore tombée, charrette abandonnée, auvent arraché, toits et fronton cassés; ces conséquences s'accumulent. Les objets gardent leur matière, couleur et position jusqu'au déplacement ou effondrement décrit. Ne jamais remettre à neuf un bâtiment déjà brisé. À la fin, montrer le même lieu enseveli, reconnaissable par les vestiges de la fontaine, de l'auvent et des colonnes.\n\nMATIÈRE ET RÉALISME\nVéritable photographie de making-of, lumière neutre/froide du hangar, lumière chaude méditerranéenne sur le petit set, minéraux volcaniques gris-brun et brefs points chauds orange au cratère. La menace principale est une nuée de gaz/cendres et de débris qui suit le sol, pas un fleuve de lave orange, un tsunami ou une explosion nucléaire. Fumée granuleuse avec fronts denses et rouleaux de turbulence, ombres et contacts avec le sol; pas mousse blanche cotonneuse, nuage décoratif ou overlay transparent sans interaction. Tuiles, bois, tissu, pierre et poussière ont des textures naturelles. Pas illustration, cartoon, jeu vidéo, plastique brillant ou bokeh extrême masquant l'action.\nCatastrophe de cinéma NON GRAPHIQUE : mouvement de fuite à distance, aucune blessure, corps brûlé, cadavre détaillé, organe, sang ou démembrement. Pas de gros plan sur la souffrance. L'ampleur se lit dans la transformation des rues et du décor.\n\nLES SEIZE INSTANTS CONSÉCUTIFS DU MÊME TOURNAGE\n\nRANGÉE 1\nCASE 01 — La ville vivante : Vue large observatrice B, derrière de vrais techniciens adultes et caméra A. Au centre, un petit décor romain au sol : forum, fontaine ronde, marché à auvent rouge à gauche, petit temple à colonnes à droite, rue vers le Vésuve miniature au fond. De minuscules Romains ADULTES vivent dans les rues : marchande avec amphore, porteur, passants, homme tirant une petite charrette. Le volcan est calme. Les bâtiments et habitants sont clairement petits face aux techniciens normaux.\nCASE 02 — Action, le marché : Même cadrage et mêmes proportions. En périphérie, le réalisateur fait un bref geste de départ; la réplique prévue est Action ! GO !, sans texte imprimé. Au centre, la marchande à étoffe ocre tend une amphore à un client en tunique bleue; la petite charrette chargée passe près de la fontaine. Le vrai récit est déjà la vie romaine, pas le geste du réalisateur.\nCASE 03 — La première secousse : La petite place tremble : eau de la fontaine ondulée, amphore qui bascule de l’étal, roue de charrette soulevée contre un pavé. Marchande et client se retournent vers le volcan; quelques habitants se retiennent au bord des murs. Premiers indices matériels, aucun énorme nuage encore. Le plateau et la caméra A gardent leur place.\nCASE 04 — Le Vésuve se réveille : Une fissure chaude apparaît dans le cratère du même petit Vésuve au fond. Un premier jet de cendres sombre monte directement depuis ce cratère. La marchande rattrape le bras du client; les autres minuscules Romains lèvent la tête. La ville reste intacte, la menace a une origine visible au fond du décor.\n\nRANGÉE 2\nCASE 05 — L’éruption : Le cratère du Vésuve éclate : colonne verticale de cendres gris-brun, projections minérales et quelques points incandescents à la source. Le petit cône reste fixe, beaucoup plus bas que les vrais techniciens, tandis que son panache grandit au-dessus du set sans atteindre le toit du hangar. Ville encore largement visible sous la colonne; pas champignon atomique ni bombe.\nCASE 06 — Les premiers débris : Les premiers grains de ponce et cendres tombent sur les toits de tuiles et le forum. Une amphore est renversée près de l’auvent rouge; la charrette se met en travers de la rue. Les Romains couvrent leur tête avec leurs étoffes et quittent les étals. Les retombées viennent du panache arrière, pas d’une pluie uniforme de studio sans cause.\nCASE 07 — Fuir le volcan : Les petits habitants courent depuis le fond de la rue VERS le forum puis vers l’issue avant gauche, donc à l’opposé du volcan. La marchande ocre et le client bleu passent près de la fontaine; la charrette abandonnée gêne un passage. Derrière eux, le panache devient plus lourd. L’équipe moderne reste hors du décor et continue de filmer, pas de plan sur son visage.\nCASE 08 — La nuée dévale : La partie basse du panache s’effondre sur les pentes du Vésuve : un front de cendres dense gris-brun dévale le petit relief vers la ville. Le trajet cratère-pente-premiers bâtiments est visible dans un seul champ. Les façades avant restent dégagées; le danger n’est pas encore partout. Masse granuleuse rapide au ras du sol, pas boule de coton ou vague d’eau.\n\nRANGÉE 3\nCASE 09 — Le premier quartier touché : Le front de nuée atteint les maisons les plus proches du volcan au FOND du set. Leurs tuiles se soulèvent, une petite toiture arrière s’effondre, poussière et fragments partent vers l’avant avec le flux. Le forum, la fontaine et les habitants en fuite restent visibles devant cette limite nette. Montrer la collision et un bâtiment qui change réellement d’état, pas seulement de la fumée derrière une ville intacte.\nCASE 10 — La rue est engloutie : La nuée traverse la même rue depuis l’arrière vers l’avant; une moitié arrière de la ville disparaît sous les cendres pendant que la moitié avant est encore reconnaissable. Les corniches de deux maisons tombent dans le même sens; les silhouettes minuscules se pressent vers la sortie avant gauche. Aucun retour au marché calme ni changement de ville à cette nouvelle rangée.\nCASE 11 — Le marché bascule : Le bord dense de la nuée atteint le forum. L’auvent ROUGE à gauche est arraché de ses poteaux et la même charrette se renverse. Des fragments de l’étal tombent contre la fontaine. La marchande et le client sont de petites silhouettes à la marge avant gauche, partiellement occultées par la poussière; ne pas représenter de blessures. Repères du plateau moderne encore visibles aux extrémités.\nCASE 12 — Le temple cède : La nuée frappe le petit temple à DROITE. Une partie de son fronton et deux colonnes s’écroulent vers le forum; les autres bases restent là où elles étaient. Dernières toitures visibles pliées ou ensevelies. L’action porte sur l’architecture et la transformation du lieu; les Romains sont désormais masqués dans ce petit monde, pas projetés vers les techniciens.\n\nRANGÉE 4\nCASE 13 — La ville disparaît : Climax : une nappe opaque et dense de cendres roule sur toute la miniature jusqu’au bord avant du décor. Quelques sommets de colonnes et fragments de toiture émergent encore, déjà cassés. Le hangar, le haut du cyclorama et une caméra moderne latérale restent lisibles : c’est toujours une petite catastrophe filmée en studio, pas un extérieur réel ni le studio entier détruit.\nCASE 14 — Les cendres retombent : Même angle. Le panache près du sol commence à se dégager, révélant une surface de cendres irrégulière avec bâtiments AFFAISSÉS, bouts de murs et temple tronqué. Le tissu rouge du marché est maintenant un petit fragment inanimé, accroché aux débris près de la fontaine presque enterrée. Les pertes sont persistantes : aucun toit intact restauré, aucune nouvelle foule.\nCASE 15 — Pompéi ensevelie : La poussière laisse voir le résultat : mêmes rues presque remplies de cendres, même fontaine dont seul le bord supérieur dépasse, bases de colonnes à droite et quartiers arrière écroulés. Zéro habitant identifiable dans la ville et aucun corps montré. Le petit Vésuve fume encore au fond. Les vrais techniciens restent debout en périphérie, un opérateur légèrement en retrait; ils ne deviennent pas le sujet.\nCASE 16 — Le même lieu, détruit : Dernière vue large exactement dans la géographie de la première case : même caméra A, mêmes techniciens normaux sur les bords, même haut hangar bleu. Au CENTRE, la Pompéi miniature est ensevelie, marché détruit, temple partiellement effondré, fontaine presque enterrée. Les reliefs brisés restent sous la couche de cendres; pas de ville intacte simplement saupoudrée. Aucun Romain identifiable, aucun corps détaillé. Le Vésuve continue de fumer. Fin sur la conséquence de la scène, jamais un portrait du réalisateur, un salut ou un reset.\n\nVÉRIFICATION FINALE : exactement4colonnes×4rangées=16photographies distinctes. Techniciens grandeur normale; toute la Pompéi, ses adultes et le cône du volcan restent MINIATURES. Marché vivant→secousse→éruption→nuée descendant de la source→collisions/effondrements→même ville ensevelie. La fin n’est pas une ville intacte seulement teintée de gris. Aucun changement d’axe, d’échelle ou de ville entre les rangées. Aucun texte imprimé.\n",
      "model_name": "GPT Image 2.5",
      "model_id": "gpt-image-2-5",
      "duration_s": "",
      "resolution": "4k",
      "aspect_ratio": "9:16",
      "settings": "GPT Image 2.5 (sunburst), text to image; Aspect ratio 9:16; Quality high; Resolution 4k; Background opaque",
      "studio_settings": "aspectRatio=9:16; quality=high; resolution=4k; background=opaque; variant=sunburst",
      "credits": 28,
      "media_url": "https://twistavo.com/prompts/storyboard-sheet/pompeii-4x4.webp",
      "media_kind": "image",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/talking-animal-sitcom-ai-video",
      "example_id": "storyboard-board",
      "example_title": "The joke as a 6-panel board before any video",
      "prompt": "Create ONE production storyboard CONTACT SHEET made of SIX genuine cinematic photorealistic AI-generated images, NOT sketches, NOT vector art, NOT diagrams. Exactly six equal distinct panels in a strict 3-column by 2-row grid, left-to-right top row then left-to-right bottom row, thin straight dark gutters and nothing else. Each individual panel is composed like a vertical 9:16 smartphone film still. No decorative border, no header, no captions, no numbers, no Arabic or English words, no subtitles, no logos, no watermark, no text on props. This sheet will be cropped into six separate shot images. Do not reproduce any reference image or existing franchise character.\n\nCHARACTER AND LOCATION LOCK: One and only one original adult macaque with short chestnut-brown realistic fur, a distinctive cream-tan oval muzzle, small round ears, two warm amber eyes, a short darker brown tuft between his brows, expressive but natural facial anatomy, and the SAME plain teal crew-neck sweatshirt in every panel. Same recognizable face, same fur pattern and garment throughout. Human-like hands with five fingers but believable primate anatomy. An ordinary warm-lit small kitchen in every panel: cream tile wall, walnut counter, wooden cutting board. Same daylight direction and photographic camera color; no other animal or person.\n\nSTORY BEATS, ONE CLEAR PHOTOGRAPHIC SHOT PER PANEL:\n1. CLOSE-UP: the same macaque reads a small blank cream doctor prescription paper at the kitchen counter, puzzled but serious. Paper has no letters at all, only empty space. His face is visible beside the paper.\n2. FACE CAMERA: the same macaque holds up ONE whole ripe yellow banana and gives the lens an unusually earnest look, as if relaying the doctor's instruction. Banana intact.\n3. INSERT: on the wooden cutting board, the macaque's hands cut THAT ONE banana across the middle using a small table knife. The two cut ends are starting to separate. His teal sleeves and fur are the same as the other frames. No second banana.\n4. MEDIUM SHOT: the macaque proudly holds the TWO distinct banana halves, one half in each hand, both cut ends clearly visible. No intact extra banana.\n5. CLOSE SHOT: he has eaten one half and is bringing the remaining half to his mouth; one empty peel lies on the counter. Show the action unmistakably, no intact banana, no duplication.\n6. CLOSE FACE-CAMERA SHOT: he has eaten both halves; he gives a cheeky knowing smirk straight into the lens. Exactly two empty peel pieces on the board, no banana flesh left.\n\nThese six frames are a coherent temporal sequence, with a natural visual punchline. No change of species, outfit, kitchen, banana count, camera grade or lighting. Avoid comical illustration style: photoreal tactile fur, fabric and kitchen materials, cinematic live-action-style stills, crisp expressions. No speech bubbles; spoken Algerian Darija and all on-screen text will be added separately in editing.",
      "model_name": "Seedream 5.0 Pro",
      "model_id": "seedream-v5-pro",
      "duration_s": "",
      "resolution": "2k",
      "aspect_ratio": "3:4",
      "settings": "Made September 23, 2026; Text to image; Aspect ratio 3:4; Resolution 2k",
      "studio_settings": "aspectRatio=3:4; resolution=2k",
      "credits": 22,
      "media_url": "https://twistavo.com/prompts/talking-animal-sitcom-ai-video/storyboard-board.webp",
      "media_kind": "image",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/talking-animal-sitcom-ai-video",
      "example_id": "gemini-kitchen-part-1",
      "example_title": "Gemini Omni Flash 1.1: the first part, voice generated by the model",
      "prompt": "GEMINI OMNI FLASH 1.1 — PART 1/2, FIRST SEVEN SECONDS OF ONE ORIGINAL COMEDY VIDEO. Generate a MOVING 9:16 cinematic social-video scene, not a still-image montage, contact sheet, animal stock footage, silent video or frozen talking head. The five attached pictures are a chronological visual storyboard of ONE original chestnut macaque wearing the SAME plain teal knitted crew-neck shirt in the SAME warm small kitchen, not five different animals or images to pan across. @Image 1: his recognizable face, blank medical note and kitchen. @Image 2: the SAME macaque holds ONE whole yellow banana. @Image 3: his hands and knife make a crosswise cut through the banana on the wood board. @Image 4: TWO separate halves of that ONE banana, one in each hand. @Image 5: his face and motion while eating. Preserve the same cream-tan muzzle, little brown tuft, amber eyes, teal top, wood board, daylight direction and backdrop. Believable primate hands and natural blinking, chewing, breathing and fur motion, with real physical action; no new banana, person or room.\n\nSTART at the blank note and quickly look directly at the viewer. 0–2.3 seconds: he lifts the one intact banana and says the first line while facing the camera. 2.3–5 seconds: he sets that banana on the board, peels it and makes ONE unmistakable crosswise knife cut, physically separating the fruit into exactly two pieces; he says the second line, sets the knife aside. 5–7 seconds: cut to a medium view, he proudly shows a half in each hand, then takes and chews one decisive bite from the FIRST half, swallowing that first half as a comedic jump cut. End this first video in a stable waist-up shot with the same macaque holding ONLY the second remaining half in his right hand, his left hand empty, as he glances toward it. Leave room for the action to continue immediately in part two. A single shared spatial axis and natural motivated cuts. Do not eat or drop the second half in this part.\n\nAUDIO is native and audible. The SAME single MALE fictional macaque speaks only these two lines, in colloquial NORTHWEST ALGERIAN DARJA AS SPOKEN IN MAGHNIA ON THE OUJDA BORDER, with natural local Maghnia/Oujdi cadence and pronunciation, emphatically NOT Modern Standard Arabic, eastern Arabic, Cairo, Casablanca or a generic dubbed newsreader. Record the actual colloquial words below, NOT a translation, not an explanation, no added narration. Say, deadpan with a small pause: «الطبيب قالّي: نقص من البنان.» Then, while cutting: «قطّعتها على زوج...» Pronounce «زوج» in western Algerian border vernacular. Mouth movement synchronized on face shots. Small natural room tone and slicing sound only; no instrumental music, no laughter track. No generated text, subtitles, graphics, brands, watermark or doctor on-screen. This is part ONE only; do not give the last punchline yet.",
      "model_name": "Gemini Omni Flash 1.1",
      "model_id": "gemini-omni-flash-1-1",
      "duration_s": "7",
      "resolution": "720p",
      "aspect_ratio": "9:16",
      "settings": "Made September 23, 2026; Reference to video, 5 reference images (board panels 1 to 5); Aspect ratio 9:16; Duration 7 s; Resolution 720p; Native audio: the model voices the lines",
      "studio_settings": "aspectRatio=9:16; mode=reference-to-video; resolution=720p; duration=7",
      "credits": 181,
      "media_url": "https://twistavo.com/prompts/talking-animal-sitcom-ai-video/gemini-kitchen-part-1.mp4",
      "media_kind": "video",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/talking-animal-sitcom-ai-video",
      "example_id": "seedance-kitchen-full",
      "example_title": "Seedance 2.5: the whole joke in one run from the same board, lip-synced to a voice file",
      "prompt": "Create one finished 12-second vertical 9:16 live-action-style comedy VIDEO, not a contact sheet, slideshow, frozen photograph, or talking portrait. All 12 seconds have real continuous subject/action motion, natural blinks, breathing, fur and sleeve movement, hand motion, chewing, and visible mouth articulation timed to @Audio 1. One original adult chestnut macaque with the cream-tan muzzle, short dark tuft, amber eyes and plain teal knitted crew-neck top from the references, in the same warm kitchen at the same wooden cutting board. No other person or animal. Warm natural light, believable primate anatomy, close-to-medium edits, fast readable social-video rhythm; serious deadpan acting is the joke.\n\nThe six images are a temporal storyboard, not six static frames to display. @Image 1 supplies the puzzled opening reading a blank medical note; @Image 2 supplies the same macaque holding ONE whole banana to camera; @Image 3 supplies the tight insert of the cut; @Image 4 supplies the TWO pieces, one in each hand; @Image 5 supplies the eating action; @Image 6 is a FACE-ONLY identity/expression reference for the final knowing look, NOT a reference for banana pieces remaining on the table. Keep one consistent macaque, outfit, room, board and banana throughout; nothing should jump, multiply or change hands unnaturally.\n\n0–3 seconds: he lowers the blank note, looks at the camera and raises his one whole banana as he delivers the doctor's instruction. 3–5.3 seconds: cut to his hands, he peels that ONE banana and makes ONE visible crosswise cut right through it into precisely two halves, placing the small knife safely aside, saying he cut it in two. 5.3–8.9 seconds: brief proud reveal with one half in each hand; then he visibly brings the first half to his mouth, bites, chews and swallows it, and does the same to the second half with comic haste. By 9 seconds both halves have been eaten, hands are empty, and only peel remains on the board. 9–12 seconds: face-camera close shot as he delivers the punchline with a small eyebrow lift, mouth moving naturally, then a brief cheeky silent look directly into lens. Do not leave any edible banana flesh in the final shot. Never cut to an extra fruit, another location, or a stationary hold instead of the physical act.\n\n@Audio 1 is the authoritative 12-second original Algerian Darija MALE voice and cadence, with four phrases and planned pauses. Synchronize the visible speech and cutting/eating to this reference; do not change, translate, replace or repeat the dialogue: «الطبيب قالّي: نقص من البنان.» then «قطّعتها على زوج...» then «وكلّيت الزوج!» and finally «قالّي نقص، ما قالّيش حبّس.» Light kitchen room tone and small synchronized slicing/chewing sounds are fine; no music, no subtitles, no on-screen words, no logos or watermarks. The note remains blank: all exact subtitles will be added in editing, not generated into the picture.",
      "model_name": "Seedance 2.5",
      "model_id": "seedance-2.5",
      "duration_s": "12",
      "resolution": "480p",
      "aspect_ratio": "9:16",
      "settings": "Made September 23, 2026; Reference to video, 6 reference images (board panels 1 to 6) and 1 audio reference (the voice file); Aspect ratio 9:16; Duration 12 s; Resolution 480p; Audio on, bitrate high",
      "studio_settings": "aspectRatio=9:16; duration=12; resolution=480p; generateAudio=true; bitrateMode=high",
      "credits": 309,
      "media_url": "https://twistavo.com/prompts/talking-animal-sitcom-ai-video/seedance-kitchen-full.mp4",
      "media_kind": "video",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/talking-animal-sitcom-ai-video",
      "example_id": "gemini-sofa-duo",
      "example_title": "Two characters, two voices: the one clean take out of ten",
      "prompt": "Original photorealistic Algerian comedy sketch with exactly TWO anthropomorphic macaques, zero humans. @Image1 defines these two existing characters: LEFT, stocky grey-brown macaque wearing a chunky cream roll-neck sweater; RIGHT, slimmer brown macaque with large ears and dark quiff wearing a navy zip hoodie and dark trousers. Preserve faces, fur, builds and outfit colours. Clothes plain; no emblem or visible writing. The reference is an identity bible, not a fixed pose. A modest warm Algerian living room, sofa and low tea table, evening lamp. Natural sitcom medium two-shot with one motivated closer reaction, no random montage. Spoken dialogue in informal western Algerian Darija (Maghnia/Tlemcen), not formal Arabic, not a narrator. LEFT has a lower calm voice, RIGHT a lighter cheeky voice; never swap speakers. Native room ambience, clear humanlike speech and naturally audible shared laughter. No music, subtitles, logos, television insert, applause or laugh track. FIRST HALF of one natural conversation. RIGHT keeps his plain phone face down and slides it farther away with one finger, avoiding it; LEFT laughs at the obvious self-deception. No bank name, balance, UI or real financial advice. In 0.5-8.5 seconds perform these three lines in order, with clear turn taking and no overlapping speech: LEFT says once: « راك توفّر الدراهم هاذ الشهر؟ ». RIGHT says once: « راني مرتاح بزاف! ». LEFT says once: « كيفاش؟ ». End on RIGHT preparing to answer the last question. No punchline or laughter yet. No added words.",
      "model_name": "Gemini Omni Flash 1.1",
      "model_id": "gemini-omni-flash-1-1",
      "duration_s": "9",
      "resolution": "720p",
      "aspect_ratio": "9:16",
      "settings": "Made September 29, 2026; Reference to video, 1 reference image (the two characters); Aspect ratio 9:16; Duration 9 s; Resolution 720p; Native audio: the model voices both characters",
      "studio_settings": "aspectRatio=9:16; mode=reference-to-video; resolution=720p; duration=9",
      "credits": 232,
      "media_url": "https://twistavo.com/prompts/talking-animal-sitcom-ai-video/gemini-sofa-duo.mp4",
      "media_kind": "video",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/talking-dog-talk-show-ai-video",
      "example_id": "dog-photo",
      "example_title": "The dog: a phone-style photo that fixes the look",
      "prompt": "Photorealistic casual iPhone-style close-up selfie angle: Bruno, a 4-year-old cream-golden retriever male dog with a soft fluffy coat, warm brown eyes, a small white patch on the chest and slightly floppy ears, face filling the frame, big confident grin, outdoors in a backyard with soft bokeh, natural golden-hour light. No text, no watermark, no logo.",
      "model_name": "GPT Image 2",
      "model_id": "gpt-image-2",
      "duration_s": "",
      "resolution": "2k",
      "aspect_ratio": "4:5",
      "settings": "Made September 17, 2026; Text to image; Aspect ratio 4:5; Quality high; Resolution 2k",
      "studio_settings": "aspectRatio=4:5; quality=high; resolution=2k",
      "credits": 61,
      "media_url": "https://twistavo.com/prompts/talking-dog-talk-show-ai-video/dog-photo.webp",
      "media_kind": "image",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/talking-dog-talk-show-ai-video",
      "example_id": "clay-talk-show-set",
      "example_title": "The show: stage key art in clay",
      "prompt": "Glossy 3D claymation diorama of a late-night talk show set: a golden retriever host sits behind a curved desk at a vintage chrome microphone, leaning in confidently with a sly grin, one paw on the desk. Around it: a small standing spotlight casting a warm cone of light, crimson curtains framing the right edge. Composition reserves open negative space on the left half for the type block (dark empty stage wall). Palette: deep charcoal #17161A stage, bone #F6F1E8 highlights, crimson #E63946 curtain accents, warm tungsten light. Cinematic lighting, shallow depth of field, premium playful 3D render. No text, no letters, no logos, no watermark. Full-bleed 3:2 landscape composition, edge-to-edge, filling the entire canvas — NO border, NO frame, NO rounded capsule, NO corner dots. Punchy contrast, committed saturated palette, commercial editorial grade. IMPORTANT: absolutely no text, no letters, no logos, no captions, no UI, no watermarks anywhere in the image.",
      "model_name": "GPT Image 2",
      "model_id": "gpt-image-2",
      "duration_s": "",
      "resolution": "2k",
      "aspect_ratio": "3:2",
      "settings": "Made September 17, 2026; Image to image, 2 reference images; Aspect ratio 3:2; Quality high; Resolution 2k",
      "studio_settings": "aspectRatio=3:2; quality=high; resolution=2k",
      "credits": 61,
      "media_url": "https://twistavo.com/prompts/talking-dog-talk-show-ai-video/clay-talk-show-set.webp",
      "media_kind": "image",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/talking-dog-talk-show-ai-video",
      "example_id": "push-in-storyboard",
      "example_title": "The opening move: a 6-panel storyboard",
      "prompt": "Storyboard for a 16:9 cinematic brand film, exactly six panels arranged in a 3x2 grid, each panel showing the SAME single continuous slow camera push-in, NOT six different scenes, no panel borders text, no letters anywhere. Subject: a photoreal golden retriever as the celebrity guest on a late-night talk show stage. Panel 1: very wide establishing shot of a dark elegant studio stage, charcoal backdrop, warm golden spotlight glow, a vintage chrome microphone on a stand, empty stage. Panel 2: slightly closer, the golden retriever walks in from the left toward the microphone. Panel 3: medium shot, dog sits at the mic stand, head alert, warm stage light. Panel 4: closer medium, dog tilts its head as if speaking, confident amused expression. Panel 5: close-up of the dog's face, microphone blurred in foreground, spotlight on fur. Panel 6: final extreme close-up, dog looks directly at the camera with a sly talk-show host grin. Consistent look: deep charcoal stage #141416, warm tungsten spotlight, bone-white highlights, cinematic grade, locked exposure, shallow depth of field, premium film photography. No text, no letters, no logos, no watermarks, no captions.",
      "model_name": "GPT Image 2",
      "model_id": "gpt-image-2",
      "duration_s": "",
      "resolution": "2k",
      "aspect_ratio": "16:9",
      "settings": "Made September 17, 2026; Text to image; Aspect ratio 16:9; Quality high; Resolution 2k",
      "studio_settings": "aspectRatio=16:9; quality=high; resolution=2k",
      "credits": 61,
      "media_url": "https://twistavo.com/prompts/talking-dog-talk-show-ai-video/push-in-storyboard.webp",
      "media_kind": "image",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/talking-dog-talk-show-ai-video",
      "example_id": "stage-push-in",
      "example_title": "The opening shot: a slow push-in to the host",
      "prompt": "A single continuous slow cinematic camera push-in, one unbroken take, no cuts, no camera shake, no zoom pulses: a photoreal golden retriever sits at a vintage chrome microphone on a deep charcoal late-night talk-show stage. Camera starts very wide: the dog small on a dark stage with one warm tungsten spotlight, crimson curtain bokeh in the far background. Camera glides forward steadily, staying centered on the dog, the spotlight warming as we approach: medium shot of the dog alert at the mic, then close-up: the dog tilts its head slightly and gives a sly amused talk-show grin directly at the camera. Resolves on an extreme close-up of the dog's face, warm spotlight on the fur, shallow depth of field, dark seamless charcoal background behind. Deep charcoal stage #17161A, bone-white rim light #F6F1E8, crimson curtain accent #E63946, warm tungsten glow, locked exposure and white balance, consistent grade, minimal motion blur, premium film look, photorealistic. No text, no letters, no logos, no watermark, no captions.",
      "model_name": "Seedance 2.5",
      "model_id": "seedance-2.5",
      "duration_s": "15",
      "resolution": "1080p",
      "aspect_ratio": "16:9",
      "settings": "Made September 17, 2026; Image to video, 1 reference image; Aspect ratio 16:9; Duration 15 s; Resolution 1080p; Audio off",
      "studio_settings": "aspectRatio=16:9; duration=15; resolution=1080p; generateAudio=false; bitrateMode=standard",
      "credits": 2058,
      "media_url": "https://twistavo.com/prompts/talking-dog-talk-show-ai-video/stage-push-in.mp4",
      "media_kind": "video",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/talking-dog-talk-show-ai-video",
      "example_id": "voice-lip-sync",
      "example_title": "The joke: the dog says the voice line",
      "prompt": "The cream-golden retriever dog named Bruno from the reference photo talking directly to camera as a comedic late-night talk show host, delivering the exact voice lines from the audio with moving mouth, lips synced to the speech, confident cheeky expressions, subtle head tilts, eyebrows raising, close to medium shot, sitting on the couch in the living room from the reference image, natural daylight, photorealistic, cinematic depth of field. Continuous single take, no cuts, no camera shake, no text, no watermark.",
      "model_name": "Seedance 2.5",
      "model_id": "seedance-2.5",
      "duration_s": "8",
      "resolution": "720p",
      "aspect_ratio": "9:16",
      "settings": "Made September 17, 2026; Image to video, 1 reference image; Audio input: the voice line (MP3); Aspect ratio 9:16; Duration 8 s; Resolution 720p; Audio off",
      "studio_settings": "aspectRatio=9:16; duration=8; resolution=720p; generateAudio=false; bitrateMode=standard",
      "credits": 481,
      "media_url": "https://twistavo.com/prompts/talking-dog-talk-show-ai-video/voice-lip-sync.mp4",
      "media_kind": "video",
      "date_tested": "2026-11-18"
    },
    {
      "page_url": "https://twistavo.com/prompts/gpt-image-2-6",
      "example_id": "movie-poster",
      "example_title": "Retro movie poster with a title, a tagline and credits",
      "prompt": "Retro science-fiction movie poster titled \"NEON TIDES\" in huge chrome letters, tagline \"The ocean remembers.\" under the title, a lone diver silhouetted against a glowing bioluminescent wave, small credits block at the bottom reading \"A TWISTAVO PICTURE - IN THEATERS SOON\", grainy 1980s print texture, cinematic lighting",
      "model_name": "GPT Image 2.6",
      "model_id": "gpt-image-2-6",
      "duration_s": "",
      "resolution": "2k",
      "aspect_ratio": "4:5",
      "settings": "Aspect ratio 4:5; Quality high; Resolution 2k",
      "studio_settings": "aspectRatio=4:5; quality=high; resolution=2k",
      "credits": 18,
      "media_url": "https://twistavo.com/prompts/gpt-image-2-6/neon-tides-poster.webp",
      "media_kind": "image",
      "date_tested": "2026-11-05"
    },
    {
      "page_url": "https://twistavo.com/prompts/gpt-image-2-6",
      "example_id": "product-photo",
      "example_title": "Product photo with a readable printed label",
      "prompt": "Studio product photograph of a minimalist frosted glass serum bottle with a clean printed label reading \"AURA\" and below it \"Hydrating Serum - 30 ml\", standing on wet dark stone with water droplets, soft morning side light, shallow depth of field, premium skincare ad",
      "model_name": "GPT Image 2.6",
      "model_id": "gpt-image-2-6",
      "duration_s": "",
      "resolution": "2k",
      "aspect_ratio": "4:5",
      "settings": "Aspect ratio 4:5; Quality high; Resolution 2k",
      "studio_settings": "aspectRatio=4:5; quality=high; resolution=2k",
      "credits": 18,
      "media_url": "https://twistavo.com/prompts/gpt-image-2-6/aura-serum-product.webp",
      "media_kind": "image",
      "date_tested": "2026-11-05"
    },
    {
      "page_url": "https://twistavo.com/prompts/gpt-image-2-6",
      "example_id": "infographic",
      "example_title": "Four-step infographic with numbered cards",
      "prompt": "Clean modern infographic titled \"How to recast a scene in 4 steps\" with four numbered cards in a row: \"1 Upload your clip\", \"2 Pick the face\", \"3 Preview the swap\", \"4 Download in HD\", flat line icons above each label, deep violet and white palette, generous spacing, crisp sans-serif typography",
      "model_name": "GPT Image 2.6",
      "model_id": "gpt-image-2-6",
      "duration_s": "",
      "resolution": "2k",
      "aspect_ratio": "16:9",
      "settings": "Aspect ratio 16:9; Quality high; Resolution 2k",
      "studio_settings": "aspectRatio=16:9; quality=high; resolution=2k",
      "credits": 18,
      "media_url": "https://twistavo.com/prompts/gpt-image-2-6/recast-infographic.webp",
      "media_kind": "image",
      "date_tested": "2026-11-05"
    },
    {
      "page_url": "https://twistavo.com/prompts/gpt-image-2-6",
      "example_id": "transparent-sticker",
      "example_title": "Sticker with a transparent background",
      "prompt": "Cute cartoon sticker of an astronaut cat floating with a tiny jetpack, thick white sticker outline, bold clean colors, no background",
      "model_name": "GPT Image 2.6",
      "model_id": "gpt-image-2-6",
      "duration_s": "",
      "resolution": "1k",
      "aspect_ratio": "1:1",
      "settings": "Aspect ratio 1:1; Quality medium; Resolution 1k; Background transparent",
      "studio_settings": "aspectRatio=1:1; quality=medium; resolution=1k; background=transparent",
      "credits": 9,
      "media_url": "https://twistavo.com/prompts/gpt-image-2-6/astronaut-cat-sticker.webp",
      "media_kind": "image",
      "date_tested": "2026-11-05"
    },
    {
      "page_url": "https://twistavo.com/prompts/gpt-image-2-6",
      "example_id": "animated-gif",
      "example_title": "Looping pixel-art animated GIF",
      "prompt": "Pixel-art campfire at night in a pine forest, flames flickering, sparks rising, seamless looping animation",
      "model_name": "GPT Image 2.6",
      "model_id": "",
      "duration_s": "",
      "resolution": "",
      "aspect_ratio": "",
      "settings": "Output GIF, 9 frames; Quality medium; Resolution 1k",
      "studio_settings": "",
      "credits": null,
      "media_url": "https://twistavo.com/prompts/gpt-image-2-6/pixel-campfire.gif",
      "media_kind": "image",
      "date_tested": "2026-11-05"
    }
  ]
}
