No indoor smoking.
45.25 s
Production
- Images
- ChatGPT
- Video
- Google Flow · Omni 1.1 Flash / Veo 3.1 Lite
- Sound effects
- ElevenLabs
- Music
- Suno V6
- Editing
- FFmpeg
- Story reference
- @mohammedkhattab55
Scenes
Switch on.
손가락과 실제 스위치를 별도 근접 컷으로 연결한다. 누른 다음 밝아져야 한다.
Settings
- Model
- Omni 1.1 Flash
- Requested duration
- 4 s
- Source
- 360p
- Ratio
- 9:16
- Control
- first-frame
Keep 0.25–1.25 s of the original switch take, then match exposure to the next reaction. The published clip reuses its later Flow upscale.
Input images
First-frame inputVideo prompt
Generate exactly ONE 4-second vertical9:16 video using Omni1.1Flash360p. Use v15-switch-start.png as the FIRST FRAME, not a loose ingredient. Candid iPhone main 1x rear camera home VIDEO, not cinematic film or a polished commercial. Deep focus, ordinary slightly harsh Korean ceiling light when on, mild phone sensor noise in darkness, restrained phone sharpening and realistic skin. Subtle handheld breathing drift under 1% frame width, no gimbal push-in, no zoom, no new camera angle. The same stocky middle-aged Chinese man B, messy short black hair, ivory ribbed sleeveless undershirt, navy/red plaid shorts, always barefoot, never smoking. Same white wallpaper, wood doorway, wall switch, blue floral floor quilt, low table with red/cream/navy books. Same two grey cloth closed-toe open-back slippers, grounded beside quilt, ignored until the mosquito is discovered. No extra slippers. No insect flying or enlarging, no visible insect body in this clip. Keep all essential body parts, feet and prop interactions above 82% frame height and within the central86% width; bottom15% is disposable empty floor, not an added graphic border. Frame the existing scene wider if needed. Full frame9:16 without baked-in crop, no text/music/dialogue. Keep the room's architecture stable while the man moves. This is a CLOSE-UP of the RIGHT INDEX FINGER and the EXISTING beige wall-switch button, not a wide shot. Keep this exact close crop, wall pattern, index anatomy, button location/shape and phone view. Ceiling light starts OFF. At 0.00s the fingertip hovers2cm in front of the actual button center. From 0.00s to 0.50s the hand approaches slightly while staying aligned with the button, not the blank wall. From 0.50s to 1.00s the index finger contacts and depresses the ACTUAL rocker switch once. At 1.00s the finger has pressed the actual button. From 1.00s to 1.25s the household ceiling light turns ON in response, producing an immediate cool white change and brief natural iPhone exposure correction. At 1.25s the lit wall texture and real button under fingertip are readable. From 1.25s to 1.75s he releases the button and pulls the fingertip back a few centimeters. At 1.75s the press-release is complete. From 1.75s to 4.00s his hand lowers slightly while the light stays ON, no further press. End at 4.00s with the same existing switch and the room lit. No blank-wall pressing, no extra switch, no melting fingers, no gradual magical lighting, no face acting or dialogue. Camera is braced smartphone, no drift or zoom.
Google Flow & sound
한국어 제작 요약: 동일한 방 마스터와 인물 B를 먼저 고정한다. 맨발·민소매·체크 반바지·슬리퍼 두 짝의 위치를 컷마다 대조하고, 실제 입력 첫/끝 이미지를 아래에서 확인한다.
In Google Flow, use the exact first/last image controls recorded per shot. The human world uses an ordinary iPhone-like home-video look; the mosquito world uses gritty amber macro materials. These are separate shots, not an insect growing inside a human shot.
Omni 1.1 Flash takes started at 360p. Veo 3.1 Lite takes used native 720p. Several selected 360p takes were later upscaled in Flow. The final 720 × 1280 export does not make every source native 720p.
Do not assume the requested duration equals the downloaded duration. In particular, the slipper pickup requested 4 seconds but returned 8. Inspect the file, then use frame-based in/out points.
Suno V6 music prompt used in production: Intimate sad instrumental film cue, sparse felt piano and a very soft low cello, 62 BPM, simple minor-key melody, exhausted lonely late-night feeling, sincere and vulnerable, warm slightly imperfect room sound, immediate recognizable melody from the first second, restrained dynamics, no long intro, no big orchestral build, no percussion, no drums, no beat drop, absolutely no vocals, no humming, no spoken words. Short 45-second cue suitable under quiet crying and a deadpan dark comedy; gentle unresolved repeating motif, leave space for sound effects.
62 BPM and 45 seconds were prompt requests, not measurements. The selected Suno result was approximately 69.96 seconds. The final film uses selected segments at 14.25–21.75, 24.50–26.25, 28.7917–32.0417 and 36.0417–37.625 seconds; human shots have no sad-music stem.
ElevenLabs supplied the mosquito buzz, switch and impact effects. Can and sip sounds also reuse generated scene audio. The impact is louder than the other effects; keep the final master below clipping. No audio or video download is offered here.
Editing
최종 타임라인은 24 fps / 1086 frames / 45.25 s. 집기 장면은 1초로 줄이고, 캔 개봉은 다른 손이 보이는 프레임을 덜어 시간 생략으로 연결했다. 건배는 벽에 닿기 전에 끊는다. 모기 컷에서만 슬픈 음악을 이어 붙이고, 마지막 4프레임은 모든 소리를 끊은 뒤 1프레임 급타격과 큰 짝 소리를 배치한다. 마지막 손 화면 위에 작은 agi.geek·블러·렌즈 피 방울을 합성했다. 이어 국토교통부·LH 생활수칙 포스터의 선택한 상단만 1초간 두 바퀴 회전·확대하고 4.5초 정면 유지한다. 기관 표기는 보존한다. No closing spoken line was recorded; the final film contains no added narration. This guide preserves the original generation prompts and explains subsequent edits separately. Final colour: user-selected restrained B grade on human shots only. Preserve the mosquito amber materials, the unlit opening and the original audio. Human grade: colorbalance rs=-0.008, bs=0.008, rm=-0.008, bm=0.006 with preserved lightness; contrast 0.985, saturation 0.92, brightness +0.002.
By agi.geek · Updated 2026-10-19.
Prompts are the originals used in production.
Workshops & production enquiries · All works