Prompt

"Generate a 15-second ultra-funny, hyper-realistic yet slightly cartoon-exaggerated AI video in vertical 9:16 format. Cozy home living room setting: soft couch, coffee table with toys, warm lamp light, rug on hardwood floor, window with curtains. No text ever. From 0-3 seconds: Tiny white fluffy Chihuahua struts in from left, tail up, sassy and confident. Massive black-and-tan Rottweiler sprawls relaxed on the rug, stoic and calm. From 3-8 seconds: Chihuahua notices Rottweiler — explosive reaction: eyes pop huge in horror, ears flatten/snap, face contorts: quivering lips, snarling bared teeth, furrowed angry brows, wide screaming mouth, side-eye glares, pouty teary blinks, puffed indignation. Trembles violently, frantic jumps spinning in circles, paws thrashing, dramatic backward flop faint then instant rebound. Rapid zooms on shifting expressions, slow-mo on peaks. Rottweiler barely tilts head, yawns slowly, looks away bored. From 8-13 seconds: Rears up challenging, deeper snarls, eyes narrow then burst wide, body shudders intensely, flips between rage and wounded pouts. Quick cuts: close face details vs. wide absurd size contrast. From 13-15 seconds: Last big huff, shake, proud nose-high turn, struts off victoriously; Rottweiler unchanged, peaceful. Visuals: warm indoor lighting, detailed textures, AI-boosted Chihuahua expressions. Playful music with synced cartoon effects. Hilarious tiny meltdown vs. big chill."

video

"Generate a 15-second ultra-funny, hyper-realistic yet slightly cartoon-exaggerated AI video in vertical 9:16 format....

Sora 2video:sora2-text-to-video-standardTekst til video
4. feb. 2026, 19:35

Innstillinger

Leverandør
Sora 2
Modell
video:sora2-text-to-video-standard
Opprettet
4. feb. 2026, 19:35
Kreditter
60
Modus
Tekst til video
Sideforhold
portrait

Lag noe lignende

Generatoren nedenfor forutvelger modellen som brukes for denne posten, slik at du kan remikse ideen raskere.

Nye oppgaver vises her etter at du har sendt inn.