Iced tea at a warung counter
A vertical close-up of a glass of iced sweet tea on a warung counter, a hand stirs it with a straw.
The prompt
This prompt has three parts: the scene, the sound and the music. Copy all three. Leave the three labels at the start of each part as they are. The model reads them.
integrated_multimodal_description: [Shot 1] Live-action, a vertical medium close-up of a wooden warung counter in the late afternoon, a tall glass of iced sweet tea with ice cubes and beads of condensation, a row of glass jars of crackers blurred behind it. The camera holds a static shot. A woman's hand in a plain batik sleeve slides a red-and-white striped straw into the glass and stirs, and the ice clinks against the glass. overall_soundscape: Street ambience with motorbikes passing, ice cubes clinking in the glass, the soft stir of the straw. non_diegetic_music: N/A
Why it works
- The place is specific: a wooden warung counter with jars of crackers behind it.
- Ice cubes and condensation give the camera something to see.
- A static camera keeps the vertical frame steady for Reels and TikTok.
- Street sounds sit in the sound field, not in the scene text.