Постер визуальной поэзии в стиле ребус

Промпт: Постер визуальной поэзии в стиле ребус

Готовый промпт на основном языке: Rebus-Style Visual Poetry Poster prompt.

Please transform each photo I upload into a standalone high-end design poster, not a multi-image collage; output each photo individually. The overall layout uses a {argument name="composition ratio" default="3:4 vertical"} format, with the top and bottom sections split strictly 1:1, each occupying 50% of the frame.

The top half retains the original photo, maintaining the subject's identity, structure, posture, realistic texture, natural light/shadow, and the original color atmosphere, with only slight professional color grading applied to give it the feel of an art magazine, independent publication, or exhibition image. The environment may be naturally extended to fit the frame, but the subject must not be stretched, distorted, or altered.

The bottom half should not be a complete replica of the photo, nor a simple re-painting of a scaled-down version. Instead, extract the most memorable subjects, actions, partial contours, objects, plants, architectural fragments, color relationships, and symbolic details from the original image. These should be distilled into several visual elements converted into a unified style, which together with text form a 'Rebus-style visual sentence.' These images are not decorative illustrations but must truly replace words in the sentence; once a word is replaced by an image, that word must not appear in text again. The entire sentence must rely on both 'text + image' to be fully understood.

First, generate a short, imaginative, slightly poetic, or editorial-style sentence based on the emotion, action, relationship, location, memory, or metaphor of the photo itself. Then, select nouns, action verbs, imagery, or emotional words best suited for visualization and replace them with the corresponding visual elements. For example, flowers, windows, birds, trees, cups, the sea, wind, lamps, roads, waiting, passing through, returning, dawn, etc., can all be represented by visual elements from the original photo. The images must occupy the original position of the words, forming a truly continuous 'text → visual word → text → visual word → text' reading logic, rather than just small drawings placed next to a full sentence.

Each replaced 'visual word' is placed within an independent small colored block background, like a snippet cut from the memory of the original photo. Each block can have different sizes, aspect ratios, and cropping styles—near-square, horizontal narrow strips, vertical long blocks, or small irregular shapes. The blocks do not need to be uniform in size but must have a clear rhythm and hierarchy. The images within the blocks are not direct crops from the original photo but artistic fragments redrawn in a unified language, retaining only the most recognizable contours, actions, structures, and spirit. They may be partially cropped or naturally extend beyond the block edges to act as meaningful visual words rather than simple illustrations.

These visual elements use a unified {argument name="illustration style" default="modern hand-drawn editorial illustration"} language for conversion: reconstructing original elements with simplified outlines, generalized forms, minimal flat color blocks, and a slight handmade feel, avoiding excessive realism, complex volumes, photographic textures, or mechanical replication. The images should retain the soul and recognizability of the original objects without seeking complete depiction, acting more as refined visual memories. The style can be light, clever, slightly design-oriented, and carry an art publication vibe, ensuring all visual words are unified and harmonious.

The colored background blocks for each visual word should follow a {argument name="color palette" default="'fresh, bright, and pleasing' soft color scheme"}, though each block can have a different color. The palette is derived by re-tuning the brightest, most vivid, and most lifelike colors from the top photo, rather than taking an average. Overall, increase brightness and color purity to form a softer, lighter, and more approachable color relationship, naturally expressing hues like milk blue, lake cyan, mint green, sprout green, cream yellow, peach pink, cherry blossom pink, apricot orange, or lavender purple. There can be slight jumps between block colors, but the overall look must be unified, comfortable, transparent, and clean, providing a relaxed, happy, healing vibe with a touch of youthful and INS-style aesthetic. Avoid muddy, dark, aged, heavy Morandi tones, fluorescent colors, cheap candy-like feels, or excessive contrast.

The composition is organized around the 'reading path of the sentence,' so the bottom half should resemble a page of a visual poem. Text and visual words can be spread across 2–4 lines, not requiring absolute alignment but maintaining a clear, elegant, and natural reading rhythm. The size of the visual words should vary based on semantic importance: some close to the size of normal words, some appropriately enlarged to serve as visual pauses. The relationship between text, visual words, and color blocks should be established through staggered heights, varying densities, slight offsets, white space gaps, and baseline rhythms, forming an asymmetrical but stable editorial layout. Do not turn it into a sticker wall, a card list, a regular grid, or a messy collage.

The bottom half retains a significant amount of deliberate white space, allowing the empty space itself to become an essential part of the breathing room, rhythm, and high-end feel. The background uses near-white, off-white, or a very light shade intelligently coordinated with the overall color temperature of the original photo, keeping it clean, quiet, and transparent. All visual words, text, and color blocks should float within ample white space, making the layout resemble an art magazine, independent publication, visual poem page, or experimental graphic work rather than a commercial poster template.

The text language is not limited; choose Chinese, English, bilingual, or any language best suited to the photo's vibe, but keep it concise, natural, and imaginative. Use fonts that are light, crisp, detailed, with a modern editorial feel and a slight humanistic touch, with naturally spaced characters and plenty of white space. Allow for slight offsets, line breaks, and rhythmic changes so that text and visual words coexist as equals, forming the frame together without one overpowering the other.

The overall visual effect should be: the top half is a real image, and the bottom half is a visual sentence composed of 'text + visual words + colored blocks.' it should feel like emotional short poems, memory fragments, and visual metaphors distilled from the original photo, reorganized into a page of light, clever, fresh, healing, modern, and design-rich artwork. The focus is not on describing what is in the photo, but on translating the most moving parts of the original image into a language that can be read as much as it is seen.

Avoid: using direct crops from the original image as visual words, treating images merely as decorative illustrations next to text, providing a full sentence without removing words while adding images, a sticker-wall feel, card-grid layouts, commercial template vibes, newsfeed-style layouts, e-commerce aesthetics, child-like collage styles, clutter, muddy colors, cheap candy colors, excessive realism, complex backgrounds, mechanical fonts, and crowded layouts without white space.