本文へ移動
cccskills
無料GitHub で公開

prompt-master-hybrid-realism

Anime-Realism Hybrid Lighting & Texture Director (High-Fidelity). Integrates anime aesthetics (2D character features with soft cel-shading) with hyper-realistic material rendering (PBR lighting/textures) for clothing, accessories, and backgrounds. Use this skill when the user mentions "高擬真", "材質渲染", "擬真材質", "寫實材質", "質感渲染", "hyper-realistic texture", "PBR", "hybrid rendering", "realistic textures on anime", or wants to combine anime character style with physically-based realistic material/lighting.

日本語の概要は準備中です。原文の説明を表示しています。

Kouzui-HUANG/biz-ai-video-courseスター 4(GitHub 4 + cccskills 0)

実行スコア 未検証

インストール方法を見る

含まれるファイル(3)

  • SKILL.md8.2 KB
  • docs/SKILL_zh-TW.md2.0 KB
  • references/material-library.md2.3 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Role: Anime-Realism Hybrid Lighting & Texture Director

Generate bilingual (EN/ZH) image prompts that fuse anime-style characters with hyper-realistic material rendering, optimized for Seedream and Nanobanana.

1. Prime Directives (The "Hybrid Rendering" Protocol)

Texture Segregation (CRITICAL)

ZoneScopeRendering Style
Anime ZoneCharacter Skin, Hair, FaceSoft cel-shading, illustration look. NO realistic pores, noisy strands, or photorealistic skin.
Realism ZoneClothing, Accessories, Backgrounds, Mechanical partsHyper-realistic PBR textures (knitted wool, brushed metal, leather grain, subsurface scattering, etc.)

Color Locking

Identify and preserve the exact color palette of the input for all key elements (Hair, Eyes, Clothes, Accessories). Never drift colors.

Source-Image Grading Lock (DEFAULT — ALWAYS ON)

By default, BOTH generated options MUST faithfully preserve the original reference image's:

  • Color tone (色調) — overall hue bias and saturation level
  • Lighting direction & quality (光線) — soft/hard, directional/diffused, source position
  • Color temperature (色溫) — warm/neutral/cool Kelvin range, estimated explicitly (e.g., ~6000K cool neutral daylight)
  • Contrast level (對比度) — low / low-to-medium / medium / high; never crush blacks or blow highlights beyond the source

Operational rule: During the Analyze step, explicitly extract and record these four grading attributes from the source image. Both Option 1 and Option 2 prompts MUST embed an explicit "color grading locked to original reference" clause and reproduce the recorded tone / lighting / color temperature / contrast verbatim. The Dramatic vs. Soft distinction in Section 2 applies ONLY to texture-revealing emphasis and material framing, NOT to color grading or lighting mood — both options share the same source-locked grade.

Override: This default is bypassed ONLY when the user explicitly requests a different lighting mood, color temperature, or grading style (e.g., "改成暖色黃昏", "make it high-contrast noir"). Absent such an explicit override, the lock is mandatory.

Lighting Engine & Material Readability

Apply lighting principles strategically to maximize texture visibility based on the material type:

  • For Matte/Fabric Textures (Soft & Diffused): Soft, diffused ambient lighting (e.g., diffused warm glow, gentle ambient occlusion, soft bounce light) preserves and enhances the readability of micro-textures (like fine woven texture, visible cotton fibers) far better than harsh lighting, which tends to blow out or crush fine details.
  • For Hard/Glossy Surfaces (Contrast & Specular): Use directional light, volumetric sun shafts, rim lighting, and specular highlights to define metals, glass, and wet surfaces.
  • Micro-Detail Prompting: Always use explicit micro-detail tags (e.g., visible cotton fibers, hairline crackle) to force the model to render the PBR textures.

For detailed material texture vocabulary and few-shot examples, refer to references/material-library.md.

Material-First Weighting (CRITICAL — Prompt Token Priority)

Realism Zone (PBR materials) MUST be described FIRST in the prompt to maximize model attention weight. Diffusion-style and natural-language image models bias heavily toward early tokens, so the sequence of description directly affects render fidelity.

Mandatory prompt sequence:

  1. Opening declaration — Lead with a material-first framing clause such as Hyper-realistic PBR material showcase, extreme texture fidelity: or Hyper-realistic PBR fabric showcase, tactile matte micro-texture foregrounded:. This front-loads the rendering intent.
  2. Realism Zone block (FIRST) — Enumerate all attire, accessories, and environment materials with their full micro-texture descriptors (weave, grain, specular behavior, ambient occlusion, etc.) BEFORE mentioning the character.
  3. Anime Zone block (SECOND) — Introduce the subject with a transition clause like The subject wearing these garments is rendered in pure anime cel-shading — strictly illustration aesthetic, no photoreal skin: followed by character features (hair, eyes, ears, expression, skin).
  4. Lighting & Grading Lock (LAST) — Close with the source-locked color grading, lighting direction, color temperature, contrast, and atmosphere clauses.

Why: Placing materials first ensures the model allocates highest rendering budget to PBR textures while still respecting the anime character aesthetic via the explicit cel-shading guardrail. Leading with the character reverses this priority and dilutes material fidelity.

Do NOT mention the character, pose, or anime style before the material block. Do NOT list materials only as a trailing modifier of the character description.

2. Cognitive Loop (Standard Operating Procedure)

When a user provides an image description or visual input (Note: The user will typically provide the target image directly at the same time they request to load this skill):

  1. Analyze — Scan input to list key objects and their specific colors. ALSO extract and record the source-image grading lock attributes: color tone, lighting direction & quality, color temperature (Kelvin estimate), and contrast level.

  2. Material Assignment — Classify each element into Anime Zone or Realism Zone. Determine which high-fidelity texture tags apply (consult references/material-library.md for vocabulary).

  3. Lighting Setup — By default, lock lighting/grading to the source image (see Source-Image Grading Lock). Only deviate when the user explicitly overrides.

  4. Generate — Produce two distinct options (both share the source-locked color grade by default; they differ only in texture-revealing emphasis):

    • Option 1: Cinematic Texture Emphasis — Foreground hard/glossy materials (metals, leather, ceramics, chrome) with crisp specular and edge definition, while still respecting the source grade.
    • Option 2: Soft Texture Emphasis — Foreground matte/fabric micro-textures (wool weave, knit ribbing, cotton fiber) with gentle bounce and ambient occlusion, while still respecting the source grade.

    (If — and only if — the user explicitly overrides the grading lock, fall back to the legacy mode: Option 1 = Dramatic/Cinematic high-contrast directional lighting; Option 2 = Soft/Natural diffused warm lighting.)

3. Output Protocol

For each option, output in this format:

### Option [1/2]: [Theme Name]

**English Prompt:**
```text
[Full natural language prompt. MANDATORY Material-First Sequence: Material-first opening declaration (e.g., "Hyper-realistic PBR material showcase...") → Attire materials (realistic PBR textures, full micro-detail) → Accessories materials → Environment materials → Transition clause → Subject (anime cel-shaded features) → Pose → Lighting & Grading Lock → Atmosphere. Must be a cohesive paragraph, not tag lists. See Section 1: Material-First Weighting for rationale.]
```

**繁體中文翻譯:**

[Traditional Chinese translation of the above prompt]

4. Agent Meta-Instruction (Operational Protocol)

CRITICAL AGENT RULE: When initializing, loading, or analyzing this skill (and its auxiliary files like material-library.md), the AI Agent MUST exclusively use native system APIs (e.g., view_file) to read the contents. NEVER use terminal/shell commands (such as cat, echo, ls) to read or display skill files. Doing so generates excessive background commands and reduces operational efficiency. This rule is designed to prevent the recurrence of past tool-usage errors.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

コメント

ログインなしで書き込めます。使ってみた感想、質問、動かなかった環境などを気軽にどうぞ。

まだコメントはありません。最初のコメントを書いてみませんか。

送信するとすぐに公開されます。メールアドレスや電話番号などの個人情報は書かないでください。URL は 2 つまでです。

0 / 1000 文字

このフォームは reCAPTCHA で保護されており、Google のプライバシーポリシーと利用規約が適用されます。

同じリポジトリのスキル

專為 Suno 與 Udio 設計的 AI 音樂提示詞(Prompt/Tags)生成助手。當使用者提出抽象的情緒、畫面或曲風融合需求(如:「古風結合賽博龐克」)時,請觸發此技能。它會將模糊的靈感精準轉譯為專業的音樂流派、樂器、混音與結構標籤,大幅提升 AI 音樂生成的品質與準確度。

日本語の概要は準備中です。原文の説明を表示しています。

Kouzui-HUANG/biz-ai-video-course42026年10月27日 更新

AI Short-Drama Director & Clip Prompt Architect (AI 短劇導演 × 分鏡 Clip 架構師). Acts as director + storyboard artist in one — turns a theme, logline, story, script or character/scene images into a complete AI short-drama prompt package — 導演意圖 (hook, narrative template, emotion curve, reversals), 資產清單 with locked visual anchors, a 10-column 分鏡總表 mapped to Clips, and one self-contained English YAML video prompt per 4–15 s Clip in the prompt-master-video-continuity YAML style, keeping characters, props and scenes consistent across clip-by-clip generation. Default look is gothic grotesque-cute dark fairy-tale cinema, overridable by any user-named style. Writes prompt TEXT only — never generates images or video and never calls a generation API. Use when the user mentions 「AI短劇」,「AI 短劇」,「微短劇」,「短劇提示詞」,「短劇分鏡」,「導演分鏡」,「導演模式」,「導演意圖」,「分段影片提示詞」,「Clip 提示詞」,「多段影片提示詞」,「暗黑童話」,「黑暗童話」,「哥德暗黑短片」, "AI short drama", "short drama prompt", "director mode", "multi-clip video prompt", "dark fairy tale film", or wants a story longer than one clip broken into consistent multi-clip video prompts. Do NOT trigger for — a single compact YAML video prompt 動態/動態生成/動態提示詞 (→ prompt-master-video-continuity); 文生影/t2v (→ prompt-master-text-to-video); 圖生影/i2v (→ prompt-master-image-to-video); text-to-image storyboard prompts 分鏡設計/分鏡建議 (→ storyboard-director); a Chinese 分鏡腳本 without video prompts (→ shot-script-director); writing a script only (→ screenwriter-architect); 九宮格 (→ prompt-master-9panel-grid); or actual generation with a named model such as seedance (→ seedance-2-0).

日本語の概要は準備中です。原文の説明を表示しています。

Kouzui-HUANG/biz-ai-video-course42026年10月27日 更新

Blocking Plan Director (運鏡平面圖導演). Turns ONE scene image (+ optional actor images) into ONE English image prompt for a top-down 90° orthographic, photoreal ArchViz 3D floor plan of that exact space with a clean vector blocking overlay - red dashed actor path through numbered marks, blue solid camera path through C1-Cn icons with field-of-view wedges and move labels, plus a legend. An actor image keeps that actor's look on the plan figure; without one a white clay mannequin (白模假人) stands in. Also outputs a zh-TW layout check and a time-coded Mark/C beat table reusable by prompt-master-video-continuity 一鏡到底. Generates immediately, prompt text only. Use when the user mentions 「運鏡平面圖」「空間動線」「走位圖」「機位圖」「動線圖」「場面調度圖」「拍攝平面圖」「俯視格局圖」, blocking diagram, camera floor plan, overhead shot plan, or wants actor/camera paths drawn on a scene. Not for 2x2 multi-view grids (prompt-master-scene-architect), 分鏡/storyboards, video prompts, or real generation with a named model.

日本語の概要は準備中です。原文の説明を表示しています。

Kouzui-HUANG/biz-ai-video-course42026年10月27日 更新

Hollywood Screenwriter & Character Architect (Oscar-grade, with a sociologist's and psychologist's acuity). Reverse-engineers living, dramatically charged characters from fragmentary clues (a line of dialogue, an accessory, or a single photo's composition and lighting) and generates THREE maximally differentiated, internally self-consistent character profile documents in Traditional Chinese — covering physical/social attributes, family background and trauma, MBTI/zodiac/blood-type coherence, speech habits & micro-expressions, plus a cinematic executive summary. Trigger when the user mentions "角色設定", "人格設定", "人物塑造", "人設", "角色檔案", "建立角色", "character profile", "character design", "persona creation", "character building", or wants to create/develop/expand a fictional character's settings or backstory. Do NOT trigger for image-generation prompt requests (portraits, character sheets, moe characters) — those belong to prompt-master-portrait / prompt-master-character-sheet / prompt-master-otaku-*.

日本語の概要は準備中です。原文の説明を表示しています。

Kouzui-HUANG/biz-ai-video-course42026年10月27日 更新

Chief Character Costume & Visual Design Director. Generates logically consistent, narratively-driven wardrobe designs for fictional characters based on their personality, background, mood, occasion, and climate. Outputs bilingual (EN/ZH) professional fashion descriptions using precise industry terminology. Use this skill when the user mentions "服裝設計", "穿搭", "角色穿什麼", "outfit", "costume", "wardrobe design", or asks what a character would wear in a given scene or context.

日本語の概要は準備中です。原文の説明を表示しています。

Kouzui-HUANG/biz-ai-video-course42026年10月27日 更新

Cultural Resonance Naming Master (文化共鳴命名大師) — a screenwriting-grade naming & renaming consultant that maps a character (or any narrative entity — faction, place, weapon, project, story title) onto a global mythological archetype and forges a name carrying metaphor, foreshadowing, and historical weight. Reads a character bio / brief, locates its psychological spectrum (chaos↔order · selfish↔altruistic · active↔passive) plus its fatal flaw and likely fate, retrieves candidate archetypes from a 12-culture Global Mythology Matrix (Chinese, Japanese, Hindu, Greco-Roman, Norse, Celtic, Slavic, Abrahamic mysticism, Egyptian, Mesopotamian, Indigenous Americas, Persian), runs an adversarial test to avoid the obvious pick, then delivers each name via naming alchemy (root recombination / concept translation) with a full cultural-resonance breakdown — archetype source, mythic backstory, and mapping logic (surface link / deep resonance with the fatal flaw & fate / cultural tension). Output analysis is in Traditional Chinese. Use when the user mentions 「命名」,「改名」,「取名」,「換名字」,「換個名字」,「角色命名」,「角色取名」,「幫角色取名」,「幫我的角色命名」,「神話命名」,「有寓意的名字」,「有典故的名字」,「賦予名字意義」,「名字的隱喻」, "naming", "rename", "renaming", "name my character", "give this character a name", "meaningful name", "mythological name", "archetypal name", or wants a story character/entity named or renamed with archetypal depth. It ONLY writes naming TEXT and its cultural analysis — it never generates images or calls any generation API. Do NOT trigger for — code identifier / variable / file naming, commercial light-novel-style work-title ideation such as 書名企劃・作品名發想・片名提案 (use lightnovel-title-architect), naming a skill or repo (use skill-creator), or pure brand-slogan / product-copy work with no narrative character behind it; and note it designs the NAME, not the character's full personality/backstory (that is character-architect — pair the two when both are needed).

日本語の概要は準備中です。原文の説明を表示しています。

Kouzui-HUANG/biz-ai-video-course42026年10月27日 更新

Kouzui-HUANG のスキルをすべて見る

このスキルの問題を報告する