OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image

盛世长安万国来朝图

Prosperous Chang'an: Ten Thousand Nations Pay Tribute

A text-driven historical reconstruction of the source scene: an aerial view of Kaiyuan-era Chang’an, Emperor Xuanzong and Yang Guifei looking out from Hanyuan Hall, and a distant tribute procession. The configured generic portrait is used only as a face-identity anchor for Yang Guifei in this genera

盛世长安万国来朝图 — AI image creation
盛世长安万国来朝图

提示词 / Prompt

中文提示词

创作一幅电影感、依据文字重构的历史场景，以宽阔的高空鸟瞰展现开元盛世时期的长安。让皇城与含元殿成为清晰的建筑视觉锚点，以层叠宫阙屋顶和井然街道展现繁盛都城。在含元殿露台上，呈现唐玄宗与杨贵妃并肩远眺。杨贵妃是画面中主要可见的女性；本次诠释仅将已配置的通用人像作为她的面部身份参考，不声称该图是经过考证或具有权威性的杨贵妃肖像。唐玄宗呈现为与她不同的成年男性，身着唐风帝王服饰，以背向镜头的斜后方视角表现，使面部不可见；不要把女性参考的面部身份套用于他。殿宇远处以细小、无法辨认个体的使团和行进队列，表现万国来朝的繁华。采用盛世日光、帝王金、朱红与玉色点缀，并以空气透视拉开空间层次。将画面处理为依据文字的历史场景重构，不声称是精确考古复原或人物肖像。不要添加可读文字、水印或标志。

English prompt

Create a cinematic, text-driven historical reconstruction in a wide aerial establishing view of Chang'an at the height of the Kaiyuan Era. Make the imperial city and Hanyuan Hall clear architectural anchors, with layered palace roofs and orderly avenues leading toward a prosperous capital. On the Hanyuan Hall terrace, show Emperor Xuanzong of Tang beside Yang Guifei as they gaze into the distance. Keep Yang Guifei as the principal visible woman and use the configured generic portrait only as her facial-identity anchor for this interpretation; do not claim it is a verified or canonical portrait of Yang Guifei. Show the Emperor as a distinct adult male in Tang-inspired imperial robes, viewed from behind at a three-quarter angle so his face is not visible; do not apply the woman's facial identity to him. Far beyond the hall, suggest the prosperity of myriad nations coming to pay tribute with small, non-identifiable delegations and processions. Use bright golden-age daylight, imperial gold, vermilion and jade accents, and atmospheric distance. Treat the scene as a historical reconstruction from the text, not an exact archaeological or portrait claim. No readable added text, watermark or logo.

查看 API 模型

探索更多图片和视频提示词 · 生成图片 · 生成视频 · 在 AI 画布中创作

  • 特斯拉电动车核心部件示意全景

    横向概念示意海报：以未指定车型的特斯拉电动车为中心，周围安排若干模块放大细节。电池包、电驱电机、逆变器/电力电子、车载充电器、热管理回路、悬架与制动、充电接口均为整理者选定的示意模块，不是来源列明的清单，也不代表特定车型布局或工程规格。 / A landscape conceptual overview centered on a Tesla EV of unspecified model, surrounded by selected module detail callouts. Battery pack, drive motor, inverter/power electronics,

  • 日系负片里的记忆碎片

    A 9:16 candid Japanese negative-film style portrait. The adult person, unposed walk and quiet neighborhood lane are replaceable curator-selected defaults, not subject or scene details supplied by the source. The currently configured ref-10a-v1 is used as the generic person identity reference and is

  • 1girl

    gpt image2.5生成

  • 法式风情地标美食海报

    A premium, clean and elegant poster concept built from the source’s broad request. Eiffel Tower, Arc de Triomphe, ratatouille and Provençal bouillabaisse are curator-selected illustrative examples, not details stated by the source; they can be replaced in a future variant. The source example image i

  • 梦回江户浮世绘古典人物像

    A reference-led Edo-period ukiyo-e portrait transformation that preserves the supplied person’s facial identity while restyling hair, clothing and accessories in traditional Japanese fashion. The current ref-10a-v1 is the generic person preview for this workflow, not a claim about any external named

  • 威震天高定西装时尚大片

    A text-driven fashion-cover portrayal of Megatron, retaining the source's silver-gray mecha, haute-couture suit and cyberpunk neon setting; it does not claim an exact adaptation-specific design. / 依据文字创作的威震天时尚封面，保留银灰机甲、高定西装与赛博朋克霓虹场景；不声称复现某一改编版本的精确造型。