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
Approach quietly.
다시 먼 구도로 돌아와 은밀하게 다가가고 오른손을 올린다. 어색한 내리치기는 이 컷에서 제외하고 모기 화면으로 전환한다.
Settings
- Model
- Veo 3.1 - Lite
- Requested duration
- 8 s
- Source
- 720p
- Ratio
- 9:16
- Control
- first-and-last-frame
The final edit keeps source 0.75–3.50 s. Cut before the awkward lowering movement. Compare the floor slipper, doorway, switch and actor gaze across the adjoining shots.
Input images
First-frame input
Last-frame inputVideo prompt
Generate ONE8-second vertical9:16 Veo3.1Lite720p video. v15-approach-start.png is the FIRST FRAME. v15-approach-end-gaze.png is the LAST FRAME. Same fixed iPhone view from a shelf, ordinary deep focus and plain overhead household light, no cinematic film grading. The same stocky middle-aged Chinese man B, ivory ribbed tank top and navy-red plaid shorts, barefoot, never smoking. One grey slipper held by heel opening in his RIGHT HAND, exactly one far mate resting on floor. Keep room/background rigidly aligned with both anchors: wall switch x55%,y31%, outlet x57%,y49%, wood door, table/books/bowl, blue floral quilt and floorboard seams. The single far floor slipper stays at x74%,y69%, toes lower right, exact same spot/size/angle. DO NOT move or duplicate the switch to the far right edge. Camera is fully STATIC, no pan/dolly/zoom/handheld drift; only the man moves. The iPhone feel comes from deep focus, exposure and skin texture, not camera movement. All feet/hand action stay above80%height; bottom15% empty floor will be cropped later. At 0.00s he holds one slipper low beside his right hip, slightly crouched in the first frame. From 0.00s to 0.75s he turns head and eyes to SCREEN RIGHT, toward the upper right wall x88%,y31%. At 0.75s gaze is fixed on that target. From 0.75s to 2.25s he takes ONE short cautious barefoot step about20cm toward that wall, keeping the held slipper low and firm. From 2.25s to 3.50s he settles into the crouched end stance, both bare feet planted. At 3.50s the short approach is complete. From 3.50s to 4.75s he raises his right hand/slipper slowly beside his ear into the end-frame ready-to-swat pose, eyes always SCREEN RIGHT, nose pointing RIGHT. At 4.75s his right hand is raised and the target gaze remains screen RIGHT. From 4.75s to 8.00s hold the end pose with tense breathing only, no downstroke. End at 8.00s matching the last frame, BEFORE striking. No actual swat/slap/contact, no huge acting, no new insect/flying body, no self-moving or multiplying slipper. The far floor mate never moves, and the near slipper never reappears on the floor. No text/dialogue/music.
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