InkRoom
InkRoom
Public prompt创意海报

信息图 / 教育视觉图 - Collage Narrative Aesthetic Template

✓Original text is publicUpdated:
GPT 8.8/10
信息图 / 教育视觉图 - Collage Narrative Aesthetic TemplatePrompt preview
Results depend on the model, inputs and generation settings.

Full prompt

Original author text

This public page preserves the author's original prompt. Review the preview and any published evaluation, then copy the text or open it as a draft. Choose the model, references and current cost in the creation workspace before generating.

From {argument name="theme" default="future theme"} provide character, environment, object, date, and short sentence content, and distribute them into a narrative of "local perception - white space pause - full entry": the first look must be two sets of soft images at the top and bottom sandwiching a large block of paper white, with a small amount of black text in the middle forming a quiet but distinct editorial pause. The upper part uses an asymmetrical three-grid collage, with two close-up fragments stacked on one side and a larger immersive local view on the other; bold cropping allows the subject to be obscured by edges, foreground silhouettes, or repeated small shapes, establishing atmosphere through scattered tactile sensations. The lower part uses a wide main scene to carry the theme, with the character or core object facing away, sideways, or in transit, not posed, retaining sufficient environment and foreground bokeh, making the viewing feel like an accidental record. The central paper white maintains relaxed breathing: two levels of short sentences are placed at the top left, the main sentence being restrained book body text, and the second sentence smaller, lighter, and tightly spaced; a huge free-hand writing title is placed at the bottom right, creating a sense of gesture with thick and thin jumps, slightly dry-brush edges, open counters, loose connections, long tail strokes, and diagonal extensions, accompanied by a small number of small-sized notes and quotation marks or emphasis symbols compatible with the target text orthography. Regardless of the target writing system, maintain recognizable glyphs along its natural reading direction; cursive text must not be forcibly disconnected, and spaced text can establish rhythm using density variations. A line of formal high-contrast display characters is superimposed on the edge of the bottom image, transparent or swallowed by highlights; text that allows letter spacing uses wide spacing, while text that cannot be split uses word spacing, line length, and weight to gain equivalent airiness. Images are unified in a light film tone of natural daylight, yellow-green, and low-saturation cyan, with milky white highlights, low contrast, and fine grain; foreground soft focus and light mist come from real depth of field; the white background retains extremely light paper fibers, printing gray marks, and a sense of incomplete cleanliness. Use narrow white dividers to connect the photo collage and paper surface, allowing the softness of photography and the decisiveness of black handwriting to elevate each other. Avoid commercial sharpening, vivid filters, perfect centering, average columns, excessive decoration, fake aging, strong gradients, or plastic skin smoothing.

Adjust the model, settings and references before generating.

Use prompt →

Prefill first, then confirm generation and the current cost.

GPT evaluation

Overall score
8.8 / 10

GPT-6-luna

AI evaluation for creative reference

Model: GPT-6-luna Overall score: 8.8 / 10 Prompt quality: 8.5 / 10 Image quality: 8.9 / 10 Prompt–image alignment: 9.1 / 10 整体呈现完成度高、与模板高度吻合的厦门清晨叙事海报,可上线;若用于正式发布,建议校对日期与小字内容。

Prompt quality8.5 / 108.5
Image quality8.9 / 108.9
Prompt–image alignment9.1 / 109.1

Community reviews

No creator reviews yet.

View and review →