Prompt library
PROMPTS
1328 hand-tested AI prompts across image, video, and music — each with full context, variables, and a sample output. Content is authored in Traditional Chinese; the UI here is English.
02Tool (Video)
03Use case
VIDEO
PRO01VIDEO／Sora 2FEATURED
2026-04-24
Sora 15-Second Narrative Ad
15 seconds is the gold-standard length for short-form video ads. Sora 2 handles narrative instructions better than other models — you can give it a three-shot mini-story instead of just a single shot.
SAMPLE產出 15 秒三鏡頭廣告、三鏡頭間有視覺 thread 連貫、敘事弧完整、配樂配合情緒推進、最終幀有 emotional payoff。可直接進 FCP / Premiere 加文字 + 品牌 logo 收尾。
Advanced
Read
VIDEO
PRO02VIDEO／Sora 2 / Veo 3.1
2026-06-04
Image-to-Video Character Consistency: Lock In a Character with a Reference Image, No More Face Drift
2026 is the year of image-to-video — use a single character reference image so the people in Sora 2 / Veo 3.1 videos stay consistent from start to finish, without drifting.
SAMPLE一段人物與參考圖一致、不換臉的影片鏡頭。
Advanced
Read
PRO03VIDEO／Sora 2
2026-04-17
Sora 2 Vertical Customer Testimonial: Realistic Facial Performance
A testimonial-video formula for e-commerce, courses, and SaaS — 'a fictional customer with genuine-feeling emotion.'
SAMPLE15 秒 直式見證影片：十八歲女性坐在暗色咖啡廣色調的品牌空間，看著鏡頭說「禪學課程讓我第一次覺得自己不用一直忙。」中間有自然的眼神游移與機微停頓，肌膚紋理真實、嘴型與口型完全同步，結尾留一秒的兩差真實笑容。直接可當 TikTok / IG 客戶見證広告投以 CBO。
Advanced
Read