YouMind
Sign in
GPT2 x B&W Geometry

GPT2 x B&W Geometry

By xiaoxiaodong P236

Installed by
0
CategoryImage
FromYouMind

Showcase

Description

Ideal for turning photos into museum wayfinding, architectural pictograms, or editorial glyphs: identity systems, cover symbols, and exhibition graphics. The upper half retains a recognizable version of the original image; the lower half keeps only three to five key structures, reorganized with a few rounded geometric blocks and negative-space notches. The symbol must be very small and centered, with continuous white space around it. Use only black, neutral gray, and white. No gradients, textures, or extra colors. If there is text, it must be tiny and placed only at the edge. Avoid realistic rendering, colorful decoration, oversized graphics, full-bleed layouts, and cheap icon templates.

Editor's Recommendation
D

Recommended by

Dancang

Why we love this skill

Distills photos into minimalist black-and-white geometric symbols, preserving just three to five key structural cues through enclosed forms, notches, and negative space.

Best for

For visual creators who need museum wayfinding, architectural pictograms, cover symbols, or exhibition graphics.

How to use this Skill

  1. Provide your input

    Provide a photo or image.

  2. Run the Skill

    Reduce the subject to a few rounded geometric structures, then reorganize it using black, gray, white, and continuous negative space.

  3. Review your result

    Get a PNG image with a centered subject in an ultra-minimal black-and-white geometric symbol style.

Related Skills

View all
Image

GPT2 x Negative Monument

For turning everyday photos into minimalist independent-publication illustrations: exhibition studies, personal photography projects, and literary visuals. The upper half retains a recognizable version of the original photo; the lower half does not depict the subject, but instead builds a field of dense, slightly shaky, broken horizontal strokes, leaving the subject as a huge, quiet expanse of negative space. A tiny, naïve figure contrasts with, passes through, or accompanies this monument. Use no more than three colors: a warm white paper ground, one soft, bright ink color drawn from the source image, and black. The image must use flat graphic forms while retaining paper texture and slight misregistration. Avoid volumetric rendering, gradients, shadows, smooth digital rendering, and flashy multicolor treatments.

小
02k
Image

GPT2 x Editorial Visual

For creating key visuals for creative tools, digital magazines, or visual identities: brand exercises, covers, and exhibition graphics. Keep the original photo recognizable in the upper half; reframe it in the lower half with large solid-color blocks, simplified contours, fine lines, and a few rounded cards. The subject is the sole focus—do not crowd the surrounding space with a complex interface. Young, smart, and slightly playful, with a warm tech feel rather than a cyberpunk look. Draw the palette from the most vivid colors in the original image and refine them, using plenty of warm white—about one or two primary colors plus an accent. Keep text small and clear, using a condensed sans serif or a lightweight monospaced font. Avoid realism, complex shadows, gradient effects, dense UI, game interfaces, and cartoon stickers.

小
12k
Image

Geo Mark | xiaoxiaodong P277

Turn an ordinary photo into a small, modernist visual mark. The original image appears above; below, the subject is distilled into a geometric symbol with a distinct brand identity, retaining only one contour, one set of proportions, one pose, and one memorable detail. The subject resembles a small visual mark from an art book, architectural brand manual, or exhibition identity, floating in generous white space. A few fine lines, supporting geometric relationships, or abstract structures may be added. It uses the language of modernist graphic design—geometric contours, flat color blocks, simple proportions, and clear boundaries. Facial features are minimized for people, and details are reduced for buildings, leaving only the most symbolic forms. Avoid complex illustrations, complete scenes, cartoon styling, generic app icons, and the feel of a commercial logo template.

小
42k

Information

Version
v5
Last updated
Runtime credits
Usage-based
Models
Auto
Use cases
Images & design
What you get
Image
Visual styles
MinimalistFlatBlack and white

Ready to create something bolder?

GPT2 x B&W Geometry