V
VIVID
← All examples

Fall latte milk frother UGC ad

Text to video · MiniMax H3
Aspect ratio 9:16
Prompt

integrated_multimodal_description: [Shot 1] Live-action, handheld smartphone UGC style, vertical 9:16, a cozy small kitchen on a grey autumn morning, warm under-cabinet light, a small pumpkin and a cinnamon stick jar on the counter. A selfie-style medium close-up shows (S1), a woman in her late 20s with a messy blonde bun and freckles, wearing an oversized rust-colored sweater. She holds up a plain matte black handheld milk frother wand with a small metal whisk tip and no logo or text toward the camera, then says in a cheerful, cozy tone: <d>[English] Okay, this tiny thing replaced my coffee shop run.</d> The camera wobbles slightly as she lifts it. [Shot 2] At 00:03.500, the camera cuts to a close-up of a clear glass mug of warm milk on the counter: she dips the plain black frother in and switches it on, the whisk spins and the milk swirls into thick, glossy foam that rises up the glass, then she pours dark espresso through the foam so it forms soft brown layers. The camera pushes in slowly. (S1) says off-screen: <d>[English] Fifteen seconds and it's actual foam. Like, café foam.</d> [Shot 3] At 00:07.000, the camera cuts back to a selfie medium shot by the rainy window: she sprinkles a pinch of cinnamon on top, takes a sip, gets a little foam on her upper lip, laughs and wipes it off. (S1) says with a laugh: <d>[English] Pumpkin spice season, homemade. Sorry, café.</d> overall_soundscape: Quiet kitchen room tone, light rain tapping on the window, the high-pitched whir of the frother, milk bubbling and swirling, espresso pouring, a ceramic spoon clink, a short laugh. non_diegetic_music: A warm, mellow lo-fi jazz beat with soft piano and brushed drums at low volume beneath the voice, cozy and relaxed, fading out at the end.

Try this prompt

AI-generated with VIVID. AI disclosure