Authentic Taiwan Street Scenes: Night Markets, Not Generic Asia
Midjourney v7 uses a precise dictionary of Taiwan-specific elements (vertical neon signage, red lanterns, corrugated-metal arcades, scooter swarms) to avoid generating scenes that read as Japan or Hong Kong instead — for local-revitalization and food/tourism material.
Cinematic photo of a [場景類型] in Taiwan at [時間光線], authentic Taiwanese details: vertical neon signs with Traditional Chinese characters, red paper lanterns, corrugated metal awnings over an arcade walkway (騎樓), scooters parked in rows, tangled overhead power lines, [人物或主體], documentary street photography, shot on 35mm lens, [色調情緒], rich detail, photorealistic --ar 3:2 --style raw 【避免被生成成日本/香港/東南亞的關鍵】 模型預設的『亞洲街景』會混搭成四不像。對策：把台灣專屬物件當『關鍵字錨點』寫死，至少塞 3-4 個—— 台味元素字典（挑著加）： - vertical neon signs with Traditional Chinese characters（直書中文霓虹招牌，最關鍵） - 騎樓 corrugated metal awnings / arcade walkway - temple with swallowtail roof ridges, 廟口 / red lanterns - night market food stalls with steam, plastic stools - rows of scooters, betel nut stand neon 排除干擾：句末可加 --no japanese signage, kanji, sakura, hong kong skyscrapers 【常見坑】 寫『Chinese street』十之八九生成中國大陸或香港；一定要寫『Taiwan / Taiwanese』並用上面的實體物件描述，別只靠國名。
Swap the variables inside the [ ] brackets for your own content, then paste into Midjourney v7.
No other tool needed — run this prompt right here and see the result (edit the text and swap the [variables] first if you like). History lives in My generations.
Use this when a local eatery, guesthouse, tourism board, or Threads scene post needs to read as unmistakably Taiwanese at a glance. English-trained models have a vague understanding of Taiwan — just writing 'Asian street' will produce a generic Japanese- or Hong Kong-flavored scene instead. What actually works isn't naming the country, it's writing Taiwan-specific objects as keyword anchors — vertical Chinese neon signage, corrugated-metal arcades (qilou), swallowtail temple roof ridges, scooter swarms — include at least three or four and the scene 'anchors' to Taiwan. --style raw makes it read more like documentary photography and less like MJ's usual flourish. Honest note: Chinese text on signage will almost always come out garbled in MJ v7 (a known weak point) — this entry's goal is getting the mood and composition right; if the signage text needs to be legible, use Nano Banana Pro or Ideogram to fix it instead. Don't push for fine facial detail — a distant, documentary-style shot of people is the most reliable.
[場景類型]要呈現的台灣場景。例：bustling night market alley / old street with tea shops / temple square at a festival
[時間光線]時段與光感，影響氣氛。例：dusk with neon just lit / humid summer night / soft morning light
[人物或主體]畫面前景的人或物。例：a vendor stir-frying at a stall / an elderly man on a scooter / customers on plastic stools
[色調情緒]整體調色與情緒走向。例：warm nostalgic film tones / moody cinematic teal-orange / bright cheerful daylight
填下面的欄位，上方 prompt 會即時替換 [方括號] 內容。填好後按「複製組好的 prompt」直接丟進工具。
Cinematic photo of a [場景類型] in Taiwan at [時間光線], authentic Taiwanese details: vertical neon signs with Traditional Chinese characters, red paper lanterns, corrugated metal awnings over an arcade walkway (騎樓), scooters parked in rows, tangled overhead power lines, [人物或主體], documentary street photography, shot on 35mm lens, [色調情緒], rich detail, photorealistic --ar 3:2 --style raw 【避免被生成成日本/香港/東南亞的關鍵】 模型預設的『亞洲街景』會混搭成四不像。對策：把台灣專屬物件當『關鍵字錨點』寫死，至少塞 3-4 個—— 台味元素字典（挑著加）： - vertical neon signs with Traditional Chinese characters（直書中文霓虹招牌，最關鍵） - 騎樓 corrugated metal awnings / arcade walkway - temple with swallowtail roof ridges, 廟口 / red lanterns - night market food stalls with steam, plastic stools - rows of scooters, betel nut stand neon 排除干擾：句末可加 --no japanese signage, kanji, sakura, hong kong skyscrapers 【常見坑】 寫『Chinese street』十之八九生成中國大陸或香港；一定要寫『Taiwan / Taiwanese』並用上面的實體物件描述，別只靠國名。
Wool coat with knit scarf
A wool coat, knit sweater and scarf form a warm layered outfit.
Character front side and back views
Three full-body views show an original adult character in one outfit.
PRO03Premium 3D Collectible Figure Avatar
Transform the input photo into a high-end stylized 3D collectible figure…
PRO04Cherry Blossom Café Outdoor Portrait
Edit the provided image while preserving the same face identity, shape,…