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
Another world.
모기 화면에서만 따뜻한 섬유질 벽과 거친 매크로 재질로 바뀐다. 얼굴은 딱딱한 곤충 외골격으로 고정하고, 눈물·눈꺼풀·호흡으로 울음을 표현한다.
Settings
- Model
- Veo 3.1 - Lite
- Requested duration
- 8 s
- Source
- 720p
- Ratio
- 9:16
- Control
- same-first-last
Use 0.25–7.75 s at normal speed. Keep the can, cigarette, rigid needle and wings. Earlier takes developed a human mouth or teeth; the adopted take avoids that articulation. This is restrained crying, not an open-mouth sob.
Input images
First-frame inputVideo prompt
M1c v25. Generate exactly ONE Veo3.1Lite native720p 9:16 video, duration_seconds=8, outputs=1,10credits. ONLY attached v4-shot-05world.png as FIRST and LAST. Animated documentary macro photograph. Exact same insect identity, dark drooping eyelids, two long antennae, single long rigid needle proboscis, transparent wings, six planted limbs, silver can held LOW screen-left and lit cigarette screen-right. Preserve the brown CHITIN of its entire head as one rigid continuous plate, including the underside of the head at the needle root. The reference face/head shape is mechanically rigid, like a hard beetle head; its appearance never changes. The needle is fixed rigidly to the head. Only eyelids, tears, thorax respiration and smoke animate. Camera fixed, same amber fibrous wallpaper and gritty photoreal materials, same scale, no transformation. NO face articulation or lip sync. At 0.00s match source photograph. From 0.00s to 0.75s thorax visibly expands then contracts with weary respiration while wet eyes remain drooped. From 0.75s to 1.50s close eyelids further and tremble the thorax/shoulders twice, keeping the rigid head shape; at 1.50s both eyelids fully lowered and body trembling. From 1.50s to 3.00s two large transparent tears lengthen under the eyes while thorax breathes. From 3.00s to 3.50s one tear detaches and falls, at3.25s falling tear is visible beneath eye. From 3.50s to 5.00s body exhales and shakes once, eyelids stay lowered; rigid face remains identical. From 5.00s to 6.25s eyelids return to original half-closed pose and thorax contracts. From 6.25s to 8.00s continue irregular exhausted respiration, one more clear tear and cigarette smoke rising, finish matching source pose at8.00s. Silver can and cigarette stay attached and low throughout, no sipping, no flying. Audio: ONLY soft continuous quiet indoor air noise. No vocal sound of any kind, music, melody, singing, speech or buzz. No text. Important head/props inside central87.5% width and above87.5% height.
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