Community影像github.com

MuziGeek/手敷淡彩照片 (Hand Tinted Photo Memory)

將提供的照片重新風格化為手敷淡彩照片(Hand Tinted Photo Memory),保留原始主體與結構,僅添加薄透的淡彩效果。

手敷淡彩照片 (Hand Tinted Photo Memory) 是什麼?

此技能專注於將使用者提供的照片轉換為「手敷淡彩照片」風格。其核心機制是先保留照片原有的單色明暗層次,再以稀薄、透明的手工敷色輕柔地染在衣物、臉部等區域,且色層不完全覆蓋底層的銀鹽顆粒感,以模擬傳統手工著色照片的視覺效果。此技能嚴格要求保留原始照片中的所有人物、構圖與攝影色調,不允許虛構、添加無關元素或進行損壞、復古等風格化改造。它支援透過參考圖編輯工具進行操作,並提供詳細的風格機制(如 medium、composition、texture 等參數)與保留約束,確保輸出結果忠於原始輸入。此技能改編自 acesjohnny 以 CC-BY-4.0 授權的原始說明,並附有完整的出處與授權文件。

相容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/MuziGeek/photo-style-skills/tree/HEAD/skills/hand-tinted-photo-memory

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

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

預覽

來自技能 README

手敷淡彩照片 (Hand Tinted Photo Memory) preview
手敷淡彩照片 (Hand Tinted Photo Memory) preview

說明文件

手敷淡彩照片 · Hand Tinted Photo Memory

先保留照片的單色明暗,再用稀薄手敷色輕染衣物與面部,色層不完全蓋住銀鹽顆粒。

A monochrome photographic print selectively tinted with delicate hand-applied transparent color. Preserve the original photographic composition and all observed people; apply tint within broad source-derived color regions.

本方法改編自 acesjohnny 的 CC-BY-4.0 授權說明。原作者歸屬、來源與改動見 provenance.json,完整 upstream 許可及其版權聲明見 LICENSE-THIRD-PARTY.txt。

Adapted from acesjohnny's CC-BY-4.0-licensed instructions. provenance.json records the original author, pinned source and modifications; LICENSE-THIRD-PARTY.txt retains the complete upstream license and copyright notices.

原始歸屬 · Original attribution: Copyright (c) 2026 acesjohnny Adapted by MuziGeek from acesjohnny / GPT Image Style Atlas. Original style prompt licensed CC BY 4.0; modifications recorded below.

輸入分析與實際保留

  1. 讀取使用者提供的原圖;若沒有可用圖片,先請求圖片。不要用本倉庫範例代替使用者輸入。
  2. 觀察原圖主體、身份、數量、連接、遮擋、光線和畫幅。依據本 Skill 的保留約束與幾何邊界,區分需要保留及明確允許轉化的部分。樣片說明不能當作使用者輸入的事實。
  3. 使用支援參考圖編輯的可用工具,把原圖作為編輯輸入。先說明觀察到的主體,再結合下方機制及 recipe.yaml 按順序組合指令;工具名稱不是必須安裝的依賴。
  4. 預設沿用原圖比例;僅依使用者要求及本 Skill 明確寫出的構圖或幾何轉化調整。配方的 4:5 是目錄樣片比例,不授權裁去必須保留的主體。
  5. 對照輸入檢查結果;只修正發現的問題,不為了增強風格改變身份或添加無關景物。區分已完成的視覺檢查與尚未驗證的效果。

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.

風格機制 · Style mechanism

  • 先保留照片的單色明暗,再用稀薄手敷色輕染衣物與面部,色層不完全蓋住銀鹽顆粒。
  • 識別特徵:單色照片底、薄敷透明色、顆粒透出。
  • Medium anchor: A monochrome photographic print selectively tinted with delicate hand-applied transparent color.
  1. medium — A monochrome photographic print selectively tinted with delicate hand-applied transparent color.
  2. composition — Preserve the original photographic composition and all observed people; apply tint within broad source-derived color regions.
  3. texture — Keep fine photographic grain visible beneath uneven translucent brush tint, with restrained edge feathering.
  4. palette — Use a warm monochrome base and subtle source-related color on skin, garments and a few meaningful objects.
  5. lighting — Retain the original photographic tonal modeling; the tint must not repaint anatomy or replace lighting.
  6. detail — Keep observed faces and hands photographically recognizable; add no scratches, damage, invented history or retro costumes.
  7. finish — Deliver one finished image at the input aspect ratio, without comparison panels, unrequested text, logos, signatures or watermarks.

保留約束 · Preservation constraints

在實際輸入觀察結果之上應用以下約束;清單不授權憑空添加圖片中不存在的元素。

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

  • Preserve all observed people and photographic tones; add only thin selective tint without fabricated damage or historical context.
  • Source subject count, recognizable identity, essential openings and connected anatomy.
  • The complete main subject within the original frame and the intended relative placement of objects.

適用範圍與幾何邊界 · Applicability and geometry

  • 適用:合影。
  • Applies to: Group.
  • 保留所有實際人物與攝影明暗,僅在單色照片上薄染色彩;不製造破損或虛構年代。
  • Preserve all observed people and photographic tones; add only thin selective tint without fabricated damage or historical context.
  • 未明確允許的結構變化均不屬於此風格;不把這些方法解釋為復刻某位藝術家、品牌或現成作品的授權。
  • Structural changes not explicitly allowed above are outside this method. This is not permission to reproduce a named artist, brand or existing artwork.

排除項 · Avoid

  • Invented people, duplicate main subjects, extra limbs, disconnected anatomy or accidental clipping.
  • Unrequested titles, logos, signatures, watermarks, fabricated labels or before-and-after panels.
  • A generic filter without the requested medium-specific physical or optical mechanism.

驗收 · Acceptance

  • 先保留照片的單色明暗,再用稀薄手敷色輕染衣物與面部,色層不完全蓋住銀鹽顆粒。 Keep fine photographic grain visible beneath uneven translucent brush tint, with restrained edge feathering.
  • 保留所有實際人物與攝影明暗,僅在單色照片上薄染色彩;不製造破損或虛構年代。 Preserve all observed people and photographic tones; add only thin selective tint without fabricated damage or historical context.
  • 主體輪廓和必要連接清楚,效果體現具體媒介機制。 The source subject remains legible with coherent connections and a visibly implemented medium-specific mechanism.
  • 只有一張完整成圖,無無關文字、品牌或水印。 One complete finished image without unrelated lettering, brands, signatures or watermarks.

配方、來源與許可 · Recipe, provenance and license

  • recipe.yaml: structured image-editing recipe / 結構化圖像編輯配方。
  • provenance.json: original authorship, method context and example status / 原創歸屬、方法背景與範例狀態。
  • LICENSE: MIT applies to MuziGeek's original contributions / MIT 適用於 MuziGeek 的原創貢獻。
  • LICENSE-THIRD-PARTY.txt: acesjohnny · CC-BY-4.0. Adapted material retains these terms and attribution / 改編材料保留原許可和歸屬。
  • 範例中的前後圖均為 AI 合成,不是真人攝影或真實製作工藝的證據。結果會隨模型與輸入變化,不承諾相同輸出。
  • 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 不授予使用者輸入、第三方作品、人物、商標或生成平台條款之外的權利;範例許可單獨見 provenance。
  • 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.

範例狀態 · Example status

ready:原圖與效果圖的真實生成及視覺審核記錄齊全;COS 外鏈範例另保留上傳回讀憑證,不在倉庫保存圖片。ready 不代表網站已發布;公開媒體白名單發布前,圖片連結可能返回 404。

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. Ready does not mean the website is released; image links may return 404 until the public media allowlist is published.

AI 合成原圖 · Source通過審核的效果 · Approved effect

Individual skills in this repo

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

相關技能