GPT2 x Specimen Poetics Atlas
By xiaoxiaodong P241
GPT2 x Specimen Poetics Atlas
By xiaoxiaodong P241
Showcase
Description
Ideal for turning an object into a poetic classification page styled like a museum publication: visual research, exhibition catalogs, and concept posters. The image shows only a precise black-and-white photograph of part of the subject; the missing portion is completed with a large area of untouched blank space and a fragile, imperfect hand-drawn outline. A few square material samples serve as evidence. Feeling words label intangible qualities, not anatomical details. Extreme negative space, restrained asymmetry, small, coarse lowercase sans serif type, a fine border line, black-and-white photographic grain, and slight printing errors. Quiet, cerebral, gentle, archival. Avoid full-color illustrations, dense catalog grids, cute stickers, smooth vector graphics, and explanatory infographics. The original is in English and is preserved verbatim in zh-CN.md.
Recommended by
Dancang
Why we love this skill
A restrained black-and-white atlas that places material and concept side by side through partial photography, imperfect outlines, material samples, and sensory language.
Related Skills
View all
ImageGPT2 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.
ImageGPT2 x Gothic Miniature
Ideal for turning strong or complex photos into fragile, understated picture-book metaphors for literary visuals, independent publishing, and exhibition pieces. The upper half retains a recognizable version of the original image; the lower half keeps only its most symbolic features, forming a small, isolated figure. Surround it with an enormous amount of empty space and, at most, one extremely faint cast shadow. Opaque gouache with thin watercolor, dry-brush marks, pencil, uneven blacks, and hesitant edges. The main colors are charcoal black, ivory white, and soft gray, with warm peach or pale apricot used only as tiny accents. A little dark but not frightening, a little awkward but not cutesy. Avoid smooth finishes, polished CG, commercial cartoons, complex backgrounds, and cinematic lighting.
ImageGPT2 x Paused Notes
Ideal for turning everyday photos into one-page private-note illustrations: journaling, indie publishing, and exhibition vignettes. The upper half preserves the recognizable original photo; the lower half keeps only the silhouette, personality, and expression, using relaxed, broken ink lines and a small amount of light watercolor to draw the subject small. Leave plenty of white space rather than filling the page, allowing strokes to stop and edges to remain open. Take two to four colors from the original image—light, thin, and restrained, but precise. Keep text small and delicate, placing it in the corners of the white space. Avoid filling the page, smooth digital polish, a plastic feel, fluorescent colors, and commercial-style headlines.
Information
- Version
- v5
- Last updated
- Runtime credits
- Usage-based
- Models
- Auto
