Vertical 9:16 social media ad, 20 seconds, bright modern lifestyle…

The prompt behind it

Vertical 9:16 social media ad, 20 seconds, bright modern lifestyle look, soft natural window light, clean pastel-white apartment desk setup, smooth handheld feel, upbeat but relaxed mood. Main character: a Thai woman in her early twenties, friendly smile, casual oversized cream t-shirt, hair in a loose bun, speaking Thai naturally to camera in a warm, energetic content-creator voice. Light cheerful background music, low volume under the voice. SCENE 1 (0–5s): Medium close-up. She sits at a desk staring at a cluttered video-editing timeline on a laptop, sighs, rubs her eyes, then turns to the camera with a playful frustrated expression and says in Thai: "อยากได้คลิปสั้น… แต่ไม่มีเวลาตัด?" SCENE 2 (5–10s): She lifts her phone toward the camera. The phone screen shows a clean Thai web app called GenHaHa with a large text box that reads "อยากได้วิดีโอแบบไหน". She types one short sentence, taps a big generate button, and a loading animation spins. She says in Thai: "พิมพ์แค่ประโยคเดียว AI ทำวิดีโอให้เลย" SCENE 3 (10–15s): Dynamic push-in. Several vertical short videos pop up floating around her like cards — a sizzling Thai street-food clip, a beach travel clip, a cute cat clip, a product shot of sneakers — then the cards snap together into one continuous longer clip. She gestures at them and says in Thai: "จากข้อความก็ได้ จากรูปก็ได้ ต่อคลิปยาวได้ด้วย" SCENE 4 (15–20s): She smiles wide and holds the phone up next to her face. A bold rounded logo text "GenHaHa" appears center-frame with a smaller Thai caption below: "เจนฟรีวันละ 10 วิ ไม่ต้องผูกบัตร". She says in Thai: "เจนฟรีทุกวัน ไม่ต้องผูกบัตร ลองเลยที่ เจนฮาฮา" and gives a small thumbs-up. Hold on the logo for the final second. Pacing rule: each spoken line is short and must finish at least 1 second before its scene ends. Lip movement matches the Thai dialogue. Keep the character's face, outfit and room consistent across all four scenes. All on-screen text is rendered clearly and spelled exactly as written.

Settings used

Length

≈ 20 seconds

Shape

Tall

Sound

With sound