Promptcelerator
简体中文

10 秒自拍游览 20 处地标

跟着节拍硬切,并用自拍杆构图,让同一角色在每个地点都保持一致。

提示词与视频作者Zara@ZaraIrahh查看原帖 ↗

提示词

Create a 10-second cinematic hyper-lapse selfie travel video of the uploaded female character across 20 world-famous destinations in 2026. Hard cuts every 0.5 seconds synced to the beat. Handheld selfie-stick camera, wide-angle lens, close selfie framing, energetic travel-vlogger style, vibrant cinematic colors, realistic lighting, dynamic motion blur, natural crowds, and clear landmarks in every shot.

Character: cheerful woman in her mid-30s with long soft wavy hair, round glasses, expressive friendly face, and a wristwatch always on her left wrist. Personality is playful, confident, funny, charismatic, upbeat, and energetic.

Strict identity consistency across all scenes: same face, same age, same hairstyle, same glasses, same body proportions, same cheerful personality. No face morphing, gender changes, hairstyle changes, missing glasses, watch switching wrists, or outfit blending.

Locations include: Eiffel Tower Paris, Shibuya Tokyo, Times Square NYC, Colosseum Rome, Pyramids Egypt, Christ the Redeemer Rio, Big Ben London, Sydney Opera House, Grand Palace Bangkok, Taj Mahal, Great Wall China, Burj Khalifa Dubai, Hagia Sophia Istanbul, Venice Grand Canal, Machu Picchu Peru, Acropolis Athens, Sagrada Familia Barcelona, Amsterdam Windmills, Gyeongbokgung Palace Seoul, and Marina Bay Sands Singapore.

Each location features a unique stylish outfit matching the local vibe and a fun expressive pose like waving, peace sign, namaste, finger heart, laughing, pointing at landmarks, thumbs-up, or playful reactions.

Negative prompt: identity change, different ethnicity, younger or older face, blurry face, distorted hands, extra fingers, bad anatomy, low resolution, uncanny smile, missing watch, watch on right wrist, invisible landmarks, duplicate locations, outfit mixing, plastic skin, random people replacing the character.
模型
Gemini Omni
分类
对白与访谈式人物
画幅
16:9 · 1920×1080
时长
0:10
声音
原生音频
发布时间
2026年5月22日

这个镜头用到的技巧