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
Pick up the slipper.
슬리퍼 상세 컷과 집는 컷을 분리했다. 바닥 소품은 접촉 전까지 움직이지 않고, 뒤꿈치 쪽을 오른손이 가린 채 들어야 한다.
Settings
- Model
- Veo 3.1 - Lite
- Requested duration
- 4 s
- Source
- 720p
- Ratio
- 9:16
- Control
- first-and-last-frame
The prompt requested 4 s; Flow returned 8 s. Use the actual output for trimming: final pickup keeps 3.25–4.25 s (24 frames). A separate 0.5 s insert precedes it. Cut away the reaching and fidgeting; this is an edit, not a one-second generation.
Input images
First-frame input
Last-frame inputVideo prompt
Generate ONE4-second vertical9:16 video with Veo3.1Lite,720p. Use v15-pickup-tight-start.png as exact FIRST FRAME, v15-pickup-tight-end.png as LAST FRAME. Keep camera fixed like a braced iPhone on the same floor. This is a real hand contacting and picking up one slipper, not object animation. Preserve original grey cloth texture and sole geometry. Quilt is LEFT. Near slipper is lower LEFT, far mate upper RIGHT; both toes point lower right. The hand enters from UPPER LEFT and is anatomically the man's bare RIGHT HAND. The far mate remains fully stationary on the exact same floorboard throughout. The near slipper stays grounded in its first-frame footprint until fingers have firm contact. Hand reaches to the heel opening, fingers inside and thumb outside, solid grip. At 0.00s no hand is visible and both slippers are grounded and motionless. From 0.00s to 0.30s keep this starting state. From 0.30s to 0.90s only the hand reaches toward the near slipper; the slippers do not move. At 0.90s fingertips contact the near slipper's heel rim. From 0.90s to 1.60s fingers close inside the opening while thumb grips outside; the near sole stays on the floor until the grip is closed. At 1.60s grip is firm. From 1.60s to 2.60s the HAND raises the gripped slipper only3cm straight up with a small shadow gap; preserve the shoe's shape and angle, no side slide. At 2.60s this tiny lift is complete. From 2.60s to 4.00s hold the same gripped shoe and tiny gap naturally, as shown in the last frame; the far mate remains grounded and still. End at 4.00s matching the last frame. No camera movement/zoom/reframing, no pre-contact slide or rotation, no duplicate slipper, no foot, no autonomous movement or morph. No insect, text, speech or music. Ordinary overhead light and iPhone deep focus/texture, not cinematic product photography. Lowest15% of the video is disposable empty floor, important action above80%.
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