Loading…
Creator · 小小东
View original source ↗
Prompt
Apply the same treatment:
Turn each photo I upload into a separate premium-designed poster. Do not combine multiple images; output each photo separately. Use an overall 3:4 vertical composition, with the upper and lower sections in a strict 1:1 height ratio, each occupying 50% of the image.
Preserve the original photo in the upper half, maintaining the subject’s structure, realistic texture, natural lighting, and original color atmosphere. Apply only subtle, sophisticated photographic color grading to give it the quality of a lifestyle magazine, independent publication, and fine-art photography. The surrounding environment may be naturally extended to fit the aspect ratio, but the subject must not be stretched, distorted, or altered.
For the lower half, first understand the original image’s true **visual core and meaning**: determine that what matters most is not “what is present,” but “what is most worth remembering”—perhaps a subject, an action, a relationship, a contrast, an emotional moment, or a symbolic meaning. Then extract its most recognizable **subject, silhouette, pose, and narrative cues**, and reconstruct them as a playful editorial poster featuring “a real subject + small black-line doodle characters.” Do not mechanically select the largest object in the original image. Preserve the visual anchor that best represents the photo’s spirit and story, so the lower half is immediately recognizable as corresponding to the original while also feeling like an intelligent reinterpretation of it.
The real subject should retain its material qualities and identifying characteristics. Its angle, proportions, lighting, and color may be moderately refined to make its core features more distinctive. Information unrelated to the original image’s meaning may be omitted, but the key relationships supporting the theme must be preserved. Add a small number of minimalist black-line doodle characters around the subject. Their actions, positions, and interactions should be generated naturally from the original image’s form, context, and implied meaning, making them feel as though they are responding to, amplifying, or reversing the original story rather than performing random actions.
Extract the most distinctive and spirited colors from the upper photo, with moderate purification, brightening, and reorganization. Use off-white, a light color, or the most comfortable pale color from the original image as the background, while preserving ample negative space. The real subject carries the primary colors, while the small characters and text use thin black or dark-gray lines for contrast. Keep the overall look clean, light, and restrained.
The text should likewise grow naturally from the original image’s **core meaning, emotion, and visual relationships**, without directly naming the objects or relying on fixed copy. Transform the most memorable layer of meaning in the photo into extremely short, lighthearted, clever handwritten text with a slight touch of humor or wordplay, as if it were a note, thought, or voice-over left by the small characters. The text may be freely arranged along the subject’s contours, the characters’ movements, or the rhythm of the negative space. It should complete the narrative together with the characters and subject, rather than appearing like a title added afterward.
Maintain an overall balance among the **real subject, core meaning, miniature narrative, naïve lines, and ample negative space**. Whether the original image features a person, animal, plant, food, building, object, vehicle, or natural scene, first identify “what this photo is really saying” before deciding how to reconstruct it. Avoid focusing only on objects while ignoring relationships, creating cute interactions without a theme, a cartoon-sticker look, complex decoration, or a templated appearance.
💣language:{argument name="language" default="english"}Models & stability
Recommended models
Independent retest evidence
Keep exploring

An aesthetic prompt that transforms photos into 3D isometric miniature landscapes using impasto oil painting and palette-knife techniques, creating a richly tactile, handcrafted texture on paper.
Prompt
Please turn each photo I upload into a separate premium design poster. Do not combine multiple images; output each photo individually. Use an overall 3:4 vertical composition, divided into upper and lower sections with a strict 1:1 height r
A detailed 3D CG render depicting an oriental fantasy girl with long mint-green hair, using high-quality PBR materials, with a dreamy garden background.
Prompt
9:16 vertical format, high-precision 3D CG oriental fantasy sweet-cool girl character poster, 3D CG oriental fantasy girl character portrait, anime-style 3D CG character art, semi-realistic 3D character render, full body portrait. The main

A specialized prompt that creates a large 3D text object based on a character's design, incorporating the character into the scene.
Prompt
Use the attached image as the most important reference. The uploaded character must be the main subject. Preserve the face, hairstyle, hair color, eyes, outfit, body type, accessories, art style, and apparent age. Create {argument name="名