Community图像github.com

MuziGeek/photocopy-night-splice

Restyle a supplied photograph as photocopy night splice / 复印拼缝夜景. Use for this specific visual method while preserving observed subjects and structure.

photocopy-night-splice 是什么?

photocopy-night-splice is a Claude Code agent skill that restyle a supplied photograph as photocopy night splice / 复印拼缝夜景. Use for this specific visual method while preserving observed subjects and structure.

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/MuziGeek/photo-style-skills/tree/HEAD/skills/photocopy-night-splice

Installed? Explore more 图像 skills: steipete/songsee, affaan-m/frontend-design, mattpocock/improve-codebase-architecture · View all 6 →

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

预览

来自技能 README

photocopy-night-splice preview
photocopy-night-splice preview

文档

Photocopy Night Splice

Convert a photograph's subject into a photocopy night splice, combining round halftone dots and square dithering with controlled, straight splices. Preserve identifiable identity and main spatial relationships.

A night street image converted into coarse toner screens and straight registration splices. Retain a readable monochrome street plate while applying round toner halftones to shadows and square dithering to selected lit regions.

This method is adapted from VigoZhao's MIT-licensed instructions. Original author, source, and modifications are recorded in provenance.json; the full upstream license and copyright notice are in LICENSE-THIRD-PARTY.txt.

Original attribution: Copyright (c) 2026 VigoZhao Adapted by MuziGeek from VigoZhao; original-post attribution is retained where the collection provides it.

Input Analysis and Preservation

  1. Inspect the supplied image; request an image only when none is available. Never substitute a repository example for the user's input.
  2. Inspect the real subjects, identity, counts, attachments, overlaps, light and framing. Distinguish preserved attributes from explicitly permitted transformations using this Skill's preservation and geometry rules; sample descriptions are not facts about user input.
  3. Use an available reference-image editing tool. Combine the observed facts with the ordered mechanisms in recipe.yaml; its model-family label does not require an installation script.
  4. Keep the input ratio by default; change composition or geometry only as requested by the user and expressly permitted below. The recipe's 4:5 ratio is a catalog-sample default, not permission to crop protected subjects.
  5. Compare output with input and correct observed failures. Report only visual checks actually completed; stronger styling must not override identity or scene integrity.

Style Mechanism

  • Convert the photograph's subject into a photocopy night splice, combining round halftone dots and square dithering with controlled, straight splices. Preserve identifiable identity and main spatial relationships.
  • Identifying features: circular toner dots, square dithering, straight splices.
  • Medium anchor: A night street image converted into coarse toner screens and straight registration splices.
  1. medium — A night street image converted into coarse toner screens and straight registration splices.
  2. composition — Retain a readable monochrome street plate while applying round toner halftones to shadows and square dithering to selected lit regions.
  3. texture — Keep splices straight and sparse, with physical toner clumps rather than digital pixel-art object outlines.
  4. palette — Use a controlled palette appropriate to the requested medium; retain identifying source colors whenever the mechanism permits.
  5. lighting — Keep illumination internally consistent across the entire edited image, with contact shadows appropriate to the requested medium.
  6. detail — Retain source subject count, essential openings and connected anatomy; remove no identifying detail unless the permitted transformation requires it.
  7. finish — Deliver one finished image at the input aspect ratio, without comparison panels, new lettering, logos, watermarks or an external frame.

Preservation Constraints

Apply these constraints to observed content; they never authorize inventing absent subjects.

  • Source subject count, recognizable identity, main pose and connected anatomy, subject to the explicitly permitted transformation.
  • Essential openings, attachments and foreground-to-background relationships.
  • The complete main subject within the input frame; no accidental clipping.

Applicability and Geometry

  • Applies to: Night.
  • Change only the explicitly requested medium, surface or illumination; keep subject count, recognizable identity, pose, essential openings and spatial relationships.
  • Structural changes not explicitly allowed above are outside this method. This is not permission to reproduce a named artist, brand or existing artwork.

Avoid

  • Invented people, extra limbs, duplicate main subjects or disconnected anatomy.
  • Unrequested logos, decorative writing, watermarks or fabricated technical claims.
  • A generic filter that fails to implement the specified physical or optical mechanism.

Acceptance

  • Keep splices straight and sparse, with physical toner clumps rather than digital pixel-art object outlines.
  • Change only the explicitly requested medium, surface or illumination; keep subject count, recognizable identity, pose, essential openings and spatial relationships.
  • The subject remains legible with coherent connections; the requested physical or optical mechanism is visibly implemented.
  • Return one finished image without unrelated lettering, brands, frames or fabricated measurements.

Recipe, Provenance and License

  • recipe.yaml: structured image-editing recipe.
  • provenance.json: original authorship, method context and example status.
  • LICENSE: MIT applies to MuziGeek's original contributions.
  • LICENSE-THIRD-PARTY.txt: VigoZhao · MIT. Adapted material retains these terms and attribution.
  • Example before/after images are AI-generated, not photographs of real people or evidence of physical craft production. Results vary by model and input.
  • MIT grants no rights to user inputs, third-party works, likenesses or trademarks, and does not override generation-service terms; example terms are recorded separately in provenance.

Example Status

ready: the source and effect have recorded real generation and approved visual reviews. COS-hosted examples also retain upload readback receipts; their image bytes are not bundled.

AI-generated SourceApproved Effect

Individual skills in this repo

This repo contains 4 individual skills — each has its own dedicated page.

相关技能