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

暴风雨海港的疾速狂奔：电影级真人动漫融合

Racing Through the Stormy Harbor: Cinematic Live-Action Anime Fusion

A grounded action-adventure frame merges a reference-matched live subject with anime-styled elements during a dangerous sprint across a rain-soaked harbor deck.

暴风雨海港的疾速狂奔：电影级真人动漫融合 — AI image creation
暴风雨海港的疾速狂奔：电影级真人动漫融合

提示词 / Prompt

中文提示词

使用NanoBanana Pro，按照版本onepiece_storm_harbor_v7_CINEMATIC_GROUNDED_NO_STICKER创作一张电影级真人动漫融合动作冒险画面。使用提供的参考图像准确保留奔跑人物的身份。在暴风雨港口码头上安排高风险疾跑：人物在风阻中持续奔跑，海浪飞沫拍打画面，湿甲板产生反光并具有可信的脚部接触阴影。保持真人身份和场景质感 grounded，同时融入动漫式动作元素，但不得变成贴纸、贴花或扁平卡通。使用阴沉暴风雨白天光、微妙港口实用灯光、略微欠曝的黑色电影效果、匹配的阴影方向、阴沉天空下一致的柔和阴影，以及湿甲板反弹光。保留运动感、紧迫感、水滴、风吹衣物或头发和电影级景深。强制使用准确模式标签onepiece_storm_harbor_v7_CINEMATIC_GROUNDED_NO_STICKER，并执行NO_STICKER约束。

English prompt

Using NanoBanana Pro, create a cinematic anime-reality action-adventure image under the version onepiece_storm_harbor_v7_CINEMATIC_GROUNDED_NO_STICKER. Use the provided reference image to preserve the runner's identity. Stage a high-risk sprint across a stormy harbor pier: the character is actively running against wind resistance while waves and spray strike the frame, with wet deck reflections and believable contact shadows. Keep live-action human identity grounded while integrating anime-styled action elements without turning the scene into a sticker, decal, or flat cartoon. Use overcast storm daylight with subtle port practical lights, slightly underexposed noir exposure, matched shadow direction, consistent soft shadow quality beneath the dark sky, and wet-deck bounce. Preserve motion, urgency, water droplets, wind-driven clothing or hair, and cinematic depth. Enforce the exact mode label onepiece_storm_harbor_v7_CINEMATIC_GROUNDED_NO_STICKER and the constraint NO_STICKER.

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

  • 盛世长安万国来朝图

    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