Token导航 LogoToken导航

Agent Skill · 前端设计

photo-colorization(照片着色)

用于辅助图像生成、图片编辑、视觉素材处理或图像模型工作流。它适合让 Agent 根据文本生成图片、处理背景、整理视觉提示词或调用相关图像工具。使用时需要确认输入图片、版权来源、输出格式和模型限制;涉及人物、品牌、商品或公开展示素材时,应额外核对授权、真实性和内容合规边界。

photo-colorization 是前端设计类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为需要联网;许可证信息还不明确,第三方扫描已通过,按安装量在前端设计类的 10,216 个 Skill 里排第 2,664。

总安装 2,012周安装 83GitHub Stars 12下载 657核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:photo-colorization(照片着色)
来源仓库:https://github.com/eachlabs/skills
仓库路径:skills/photo-colorization
安装命令:
npx skills add https://github.com/eachlabs/skills --skill photo-colorization
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/eachlabs/skills --skill photo-colorization

这个 Skill 是做什么的

前端设计类 Skill 关注页面结构、视觉规范和组件写法,输出通常是可运行的界面代码。

用于辅助图像生成、图片编辑、视觉素材处理和图像模型工作流。适合让 Agent 根据文本生成图片、处理背景或整理视觉提示词。使用时需要确认输入图片、版权来源、输出格式和模型限制。涉及人物、品牌或公开展示素材时,应核对授权、真实性和内容合规边界。

photo-colorization 属于前端设计类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/photo-colorization

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/eachlabs/skills --skill photo-colorization;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

photo-colorization 怎么安装?

在终端执行 npx skills add https://github.com/eachlabs/skills --skill photo-colorization。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

photo-colorization 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

photo-colorization 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

photo-colorization 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

photo-colorization 用的人多吗?

公开数据是累计安装 2,012 次,近一周安装 83 次,下载 657 次,GitHub 12 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

photo-colorization 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理前端设计类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

前端设计类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
frontend-design

前端设计 · Codex、Claude

8,823,360126,072只读MIT通过
vercel-composition-patterns

Vercel 组合模式 · Codex、Claude

3,858,81625,893需要联网MIT通过
vercel-react-native-skills

Vercel React native skills 前端 · Codex、Claude

2,468,66425,878只读MIT通过
adapt

adapt 搜索 · Codex、Claude

2,027,04023,125操作浏览器未明确通过
bolder

bolder 分析 · Codex、Claude

2,004,28823,130只读未明确通过
photo-colorization

照片着色 · 本页

2,01212需要联网未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Photo Colorization

Transform black and white photographs into vibrant, realistic color images using each::sense. This skill uses AI to intelligently analyze image content and apply historically accurate, contextually appropriate colors.

Features

  • Automatic Colorization: AI detects subjects and applies natural colors
  • Historical Accuracy: Context-aware coloring for period-appropriate results
  • Portrait Enhancement: Realistic skin tones for faces and portraits
  • Landscape Restoration: Natural colors for outdoor and nature scenes
  • Vintage Photo Revival: Bring old family photos back to life
  • Batch Processing: Colorize multiple photos in sequence
  • Style Preservation: Maintains original photo quality and details

Quick Start

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Colorize this black and white photo with natural, realistic colors"}],
    "model": "eachsense/beta",
    "stream": true,
    "image_urls": ["https://example.com/bw-photo.jpg"],
    "mode": "max"
  }'

Common Use Cases

Use CaseDescriptionBest For
Family ArchivesColorize old family portraits and snapshotsPersonal restoration
Historical DocumentationPeriod-accurate colorization for archivesMuseums, historians
Portrait EnhancementRealistic skin tones and facial featuresProfessional restoration
Landscape RevivalNatural outdoor and scenic colorizationNature photography
Vintage FashionAccurate clothing and fabric colorsFashion archives
Military/War PhotosHistorical military photograph restorationMemorial projects
ArchitectureBuilding and interior colorizationReal estate, heritage

Use Case Examples

1. Automatic Colorization

Basic colorization with AI-detected colors.

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Colorize this black and white photograph. Apply natural, realistic colors based on the image content. Maintain the original quality and details."}],
    "model": "eachsense/beta",
    "stream": true,
    "image_urls": ["https://example.com/old-photo.jpg"],
    "mode": "max"
  }'

2. Historical Photo Colorization

Colorize with period-appropriate historical accuracy.

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Colorize this historical photograph from the 1940s. Use period-accurate colors typical of that era - muted tones, authentic clothing colors, and historically appropriate details. This appears to be a street scene."}],
    "model": "eachsense/beta",
    "stream": true,
    "image_urls": ["https://example.com/1940s-street.jpg"],
    "mode": "max"
  }'

3. Family Portrait Colorization

Bring old family photos to life with warm, natural tones.

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Colorize this old family portrait photo. Apply natural skin tones, realistic hair colors, and period-appropriate clothing colors. The photo appears to be from the 1950s-1960s era. Make it look warm and inviting."}],
    "model": "eachsense/beta",
    "stream": true,
    "image_urls": ["https://example.com/family-portrait-bw.jpg"],
    "mode": "max"
  }'

4. Landscape Colorization

Natural outdoor and scenic colorization.

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Colorize this black and white landscape photograph. Apply natural colors - blue sky, green foliage, brown earth tones. Make it look like a vibrant summer day while preserving the original composition and atmosphere."}],
    "model": "eachsense/beta",
    "stream": true,
    "image_urls": ["https://example.com/landscape-bw.jpg"],
    "mode": "max"
  }'

5. Portrait with Specific Skin Tones

Control skin tone colorization for accurate results.

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Colorize this portrait photograph. The subject has a medium olive skin tone and dark brown hair. Apply natural, warm skin colors with subtle pink undertones. Eyes appear to be brown. Clothing looks like a dark formal suit."}],
    "model": "eachsense/beta",
    "stream": true,
    "image_urls": ["https://example.com/portrait-bw.jpg"],
    "mode": "max"
  }'

6. Vintage Photo Colorization

Restore old photographs with era-specific styling.

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Colorize this vintage photograph from the 1920s. Apply colors that match the Art Deco era - rich jewel tones for clothing, sepia-influenced skin tones, and period-appropriate interior colors. Maintain the vintage aesthetic while adding realistic color."}],
    "model": "eachsense/beta",
    "stream": true,
    "image_urls": ["https://example.com/1920s-vintage.jpg"],
    "mode": "max"
  }'

7. War/Military Photo Colorization

Historical military photograph restoration with accuracy.

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Colorize this World War II military photograph. Apply historically accurate colors - olive drab for US Army uniforms, appropriate skin tones for the soldiers, realistic equipment colors. Maintain the somber, documentary feel of the original while adding authentic military colors."}],
    "model": "eachsense/beta",
    "stream": true,
    "image_urls": ["https://example.com/wwii-soldiers.jpg"],
    "mode": "max"
  }'

8. Architecture Colorization

Building and interior photograph colorization.

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Colorize this black and white photograph of a Victorian-era building. Apply appropriate architectural colors - red or brown brick, white trim, dark roof tiles, green copper patina if visible. Include natural sky colors and surrounding landscape elements."}],
    "model": "eachsense/beta",
    "stream": true,
    "image_urls": ["https://example.com/victorian-building.jpg"],
    "mode": "max"
  }'

9. Fashion/Clothing Colorization

Accurate fabric and fashion colorization.

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Colorize this 1960s fashion photograph. Apply era-appropriate colors - bold mod colors like orange, turquoise, and pink were popular. The model appears to be wearing a structured dress. Apply realistic fabric textures and vibrant 60s palette."}],
    "model": "eachsense/beta",
    "stream": true,
    "image_urls": ["https://example.com/1960s-fashion.jpg"],
    "mode": "max"
  }'

10. Batch Colorize Multiple Photos

Process multiple photos with consistent styling using session continuity.

# First photo in batch
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Colorize this black and white family photo from the 1950s. Apply warm, natural colors with period-appropriate tones. This is photo 1 of a series from the same family album."}],
    "model": "eachsense/beta",
    "stream": true,
    "image_urls": ["https://example.com/family-album-001.jpg"],
    "session_id": "family-album-colorization",
    "mode": "max"
  }'

# Second photo (same session for consistency)
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Colorize this second photo from the same family album. Maintain consistent skin tones and color style as the previous colorization."}],
    "model": "eachsense/beta",
    "stream": true,
    "image_urls": ["https://example.com/family-album-002.jpg"],
    "session_id": "family-album-colorization",
    "mode": "max"
  }'

# Third photo (continuing series)
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Colorize the third photo. Same family, same era. Keep the color palette consistent with previous images."}],
    "model": "eachsense/beta",
    "stream": true,
    "image_urls": ["https://example.com/family-album-003.jpg"],
    "session_id": "family-album-colorization",
    "mode": "max"
  }'

Best Practices

Image Quality

  • Resolution: Higher resolution photos yield better colorization results
  • Contrast: Good contrast in the original helps AI identify details
  • Clarity: Sharp, clear photos colorize better than blurry ones
  • Condition: Digital restoration before colorization can improve results

Prompt Tips

  • Provide context: Mention the era, location, or subject matter
  • Specify skin tones: If known, describe the subject's complexion
  • Note clothing colors: If you know original colors, include them
  • Describe the scene: Outdoor/indoor, season, time of day

Historical Accuracy

  • Research the time period for authentic color palettes
  • Consider regional variations in fashion and architecture
  • Military uniforms and equipment have specific documented colors
  • Vintage car and vehicle colors are often well-documented

Mode Selection

ModeBest ForSpeedQuality
maxFinal restorations, archival work, giftsSlowerHighest
ecoQuick previews, batch testing, draftsFasterGood

Recommendation: Use eco mode for initial tests, then max for final output.

Multi-Turn Refinement

Use session_id to iterate and refine colorization:

# Initial colorization
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Colorize this old portrait photograph with natural colors"}],
    "model": "eachsense/beta",
    "stream": true,
    "image_urls": ["https://example.com/portrait.jpg"],
    "session_id": "portrait-restoration"
  }'

# Refine the result
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "The skin tones look a bit too warm. Can you redo the colorization with cooler, more natural skin tones?"}],
    "model": "eachsense/beta",
    "stream": true,
    "session_id": "portrait-restoration"
  }'

# Further adjustment
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "The dress should be blue, not green. Please adjust the clothing color."}],
    "model": "eachsense/beta",
    "stream": true,
    "session_id": "portrait-restoration"
  }'

Error Handling

ErrorCauseSolution
Failed to create prediction: HTTP 422Insufficient balanceTop up at eachlabs.ai
Invalid image URLURL not accessibleEnsure image URL is publicly accessible
TimeoutLarge image or complex sceneSet client timeout to minimum 10 minutes
Poor colorizationLow quality sourceUse higher resolution, clearer source image

Related Skills

  • each-sense - Core API documentation
  • image-restoration - General image restoration
  • image-enhancement - Enhance and upscale images
  • face-restoration - Specialized face enhancement

平台分布

Codex

36.58%
按下载量换算240

Claude

30.07%
按下载量换算198

Cursor

16.87%
按下载量换算111

Gemini CLI

8.48%
按下载量换算56

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills