OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
乐器静物与花园丰收的写实水彩双联画
Realistic Watercolor Diptych of Musical Instruments Still Life and Garden Harvest
一张9:16竖版双联画，由左右两幅独立竖向画面组成；每幅上半部为细节丰富的写实静物摄影，下半部以水彩重新表现完全相同的静物。左幅为乐器、铜盆花束与石膏墙木地板场景，右幅为阳光花园中的夏南瓜、番茄、浆果与香草场景。
提示词 / Prompt
中文提示词
创作一张9:16竖版画布，以平衡的双联画形式并排呈现两幅独立的竖向静物作品。每幅画面的上半部是细节丰富的写实静物摄影，下半部则以更松散、更具表现力的水彩插画重新表现完全相同的布置。 左幅：呈现原声吉他、哑光黑小提琴、排箫与长笛，置于陈旧有纹理的石膏墙前和乡村木地板上；乐器旁放小型放大器，以及铜盆中的郁金香、牡丹等鲜艳花束；阳光投下复杂光影（准确中文默认值：原声吉他、哑光黑小提琴、排箫与长笛，置于陈旧有纹理的石膏墙前和乡村木地板上；乐器旁放小型放大器，以及铜盆中的郁金香、牡丹等鲜艳花束；阳光投下复杂光影）。下半部水彩须重复同一组乐器、花束与放大器，并在周围加入大胆的多色颜料飞溅。 右幅：呈现夏南瓜、黄南瓜、南瓜花、圣女果、浆果、薰衣草及其他草药，置于阳光斑驳花园中破旧且有油漆飞溅痕迹的木箱上（准确中文默认值：夏南瓜、黄南瓜、南瓜花、圣女果、浆果、薰衣草及其他草药，置于阳光斑驳花园中破旧且有油漆飞溅痕迹的木箱上）。下半部将完全相同的丰收静物重构为精致水彩，以黄色、绿色和蓝色的流动渲染及有机飞溅呈现在简洁白纸背景上。 上下部分在每幅画内清楚衔接：上半部保持细节写实摄影，下半部保持更自由的水彩表现；对应上下画面中的主体和物件完全一致。两幅画面彼此清楚区分、内容易读，不得混合各自的物件。不要人物、文字、水印或徽标。
English prompt
Create one 9:16 vertical canvas presenting two distinct portrait-oriented still-life artworks side by side as a balanced diptych. In each panel, the upper half is a detailed photorealistic still life and the lower half is a looser, more expressive watercolor illustration of exactly the same arrangement. Left panel: use 原声吉他、哑光黑小提琴、排箫与长笛，置于陈旧有纹理的石膏墙前和乡村木地板上；乐器旁放小型放大器，以及铜盆中的郁金香、牡丹等鲜艳花束；阳光投下复杂光影 (exact Chinese default: 原声吉他、哑光黑小提琴、排箫与长笛，置于陈旧有纹理的石膏墙前和乡村木地板上；乐器旁放小型放大器，以及铜盆中的郁金香、牡丹等鲜艳花束；阳光投下复杂光影). The lower watercolor must repeat those same instruments, flowers and amplifier, with bold multicolored paint splatters around the arrangement. Right panel: use 夏南瓜、黄南瓜、南瓜花、圣女果、浆果、薰衣草及其他草药，置于阳光斑驳花园中破旧且有油漆飞溅痕迹的木箱上 (exact Chinese default: 夏南瓜、黄南瓜、南瓜花、圣女果、浆果、薰衣草及其他草药，置于阳光斑驳花园中破旧且有油漆飞溅痕迹的木箱上). Below it, reinterpret that exact harvest as a delicate watercolor with flowing yellow, green and blue washes and organic splatters on a simple white-paper background. Keep both upper photographs detailed and realistic and both lower illustrations looser and more expressive, with clear horizontal transitions within each panel. Preserve the listed objects and maintain exact subject continuity from the upper half to its matching lower half. Keep the two panels visually distinct and readable; do not merge their contents. No people, lettering, watermark or logo.
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
相关作品
- AI智能换装试穿对比海报
A four-section 16:9 fashion try-on and pose showcase, using the configured generic identity reference, a coordinated outfit flatlay, a matching try-on result, and six poses.
- 20 岁希娜时尚个性海报
A vertical 9:16 Y2K street-fashion character poster using the configured generic face-identity input, with an adult Sheena design, irregular detail panels, and exact source metrics text.
- 3×3 九宫格拼贴写真
A cohesive 3×3 Korean playful studio portrait collage preserving the visible identity in the configured person reference across nine distinct poses and expressions.
- 蓝莓主题可爱风人物海报
A centered 3:4 blueberry-themed poster portrait using the configured generic face-identity reference, plush blueberry props, and exact source lettering.
- 韩风手绘涂鸦感人物海报
A Korean-style illustrated half-body portrait poster that preserves the visible identity in the configured person reference, with expressive ink-and-pastel doodle art.
- 几何折纸蓝图风蜘蛛侠
Hyper-detailed folded-paper SpiderMan blueprint preserving the source geometry, blueprint annotations, minimal paper-and-ink palette, studio lighting, crisp shadows, architectural-art style and photorealistic paper detail. The configured reference is attached only as the workflow-required generic id