← 返回 Skills 市场
germey

Face Transform

作者 Germey · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
123
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install acedatacloud-face-transform
功能描述
Analyze and transform faces via AceDataCloud API. Use when detecting face keypoints, beautifying portraits, aging/de-aging faces, swapping genders, replacing...
使用说明 (SKILL.md)

Face Transform

Analyze and transform faces through AceDataCloud's Face API suite.

Authentication

export ACEDATACLOUD_API_TOKEN="your-token-here"

Quick Start

curl -X POST https://api.acedata.cloud/face/analyze \
  -H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"image_url": "https://example.com/portrait.jpg"}'

Available APIs

Endpoint Purpose Description
POST /face/analyze Face Detection Detect face keypoints (90+ points per face)
POST /face/beautify Beautification Apply beauty/decoration effects
POST /face/change-age Age Transform Make a face look older or younger
POST /face/change-gender Gender Swap Transform facial gender characteristics
POST /face/swap Face Swap Replace one person's face with another
POST /face/cartoon Cartoon Style Convert portrait to animated/cartoon style
POST /face/detect-live Liveness Check Detect if a face image is from a live person

Workflows

1. Face Analysis

Detect faces and extract 90+ keypoints per face.

POST /face/analyze
{
  "image_url": "https://example.com/photo.jpg"
}

Response includes detailed keypoints: nose, mouth, left_eye, right_eye, left_eyebrow, right_eyebrow, contour — each as arrays of {x, y} coordinates.

2. Face Beautification

POST /face/beautify
{
  "image_url": "https://example.com/portrait.jpg"
}

3. Age Transformation

POST /face/change-age
{
  "image_url": "https://example.com/portrait.jpg"
}

4. Gender Swap

POST /face/change-gender
{
  "image_url": "https://example.com/portrait.jpg"
}

5. Face Swap

Replace the face in the target image with the face from the source.

POST /face/swap
{
  "image_url": "https://example.com/source-face.jpg",
  "target_image_url": "https://example.com/target-person.jpg"
}

6. Cartoon Style

POST /face/cartoon
{
  "image_url": "https://example.com/portrait.jpg"
}

7. Liveness Detection

POST /face/detect-live
{
  "image_url": "https://example.com/face-photo.jpg"
}

Common Parameters

Parameter Required Description
image_url Yes Source face image URL
target_image_url For swap Target image for face replacement

Gotchas

  • All face APIs are synchronous — no task polling needed, results return immediately
  • Face analyze returns 90+ keypoints per detected face, supporting multiple faces in one image
  • Face swap requires two images: source (the face to use) and target (the body to put it on)
  • All APIs are currently in Alpha stage — interfaces may evolve
  • Images should contain clearly visible, front-facing faces for best results
  • Liveness detection helps distinguish live photos from printed/screen photos
安全使用建议
What to check before installing: - Metadata mismatch: the SKILL.md requires ACEDATACLOUD_API_TOKEN but the registry metadata lists no required env vars — ask the publisher to correct the metadata and document token creation/scope. - Provenance: there is no homepage or source repo. Verify who runs "acedata.cloud" and review their privacy policy and terms (images with faces are highly sensitive data). - Data flow: using the skill sends image URLs (and likely the image bytes) to api.acedata.cloud. Do not provide images of real people, minors, or any sensitive subjects unless you trust the service and have consent. - Token security: store ACEDATACLOUD_API_TOKEN in a secure secret store, limit its permissions, and rotate/revoke it if compromised. - Autonomous use: if you allow autonomous agent invocation, the agent could call the API without further prompts — consider disabling autonomous invocation or restricting the skill if you don't want agents to upload images automatically. - Validation: request from the publisher the API documentation, privacy policy, and an explicit statement of what the token scopes and retention/processing policies are. If you cannot verify the provider, avoid using confidential or real-person images with this skill.
能力评估
Purpose & Capability
The SKILL.md describes face analysis and transformations (beautify, age, gender-swap, swap, liveness) and the HTTP endpoints shown are consistent with that purpose. Requesting an API token is appropriate for a hosted Face API. However, the skill has no homepage, no source attribution, and the registry metadata lists no required env vars despite the instructions requiring a token — that mismatch reduces confidence in provenance and metadata quality.
Instruction Scope
The instructions are limited to calling AceDataCloud HTTPS endpoints and using an ACEDATACLOUD_API_TOKEN; they do not instruct reading arbitrary local files or unrelated credentials. Payloads are image_url-based POSTs. There is no instruction to exfiltrate unrelated data, but the skill will send image URLs (and thus image data) to an external service.
Install Mechanism
This is an instruction-only skill with no install steps and no code files — minimal disk or install footprint. That lowers risk from arbitrary code installation.
Credentials
The SKILL.md explicitly requires ACEDATACLOUD_API_TOKEN, but the declared registry metadata lists no required environment variables or primary credential. That inconsistency is a red flag (metadata mismatch). The single token itself is proportionate to the skill's purpose, but the omission in metadata and lack of clarity about token scope or creation are concerning.
Persistence & Privilege
The skill does not request always: true, does not modify other skills, and has no install-time persistence. It uses the platform default allowing autonomous invocation; combine that with the external API access if you plan to let agents run autonomously.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install acedatacloud-face-transform
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /acedatacloud-face-transform 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial release of face-transform skill providing extensive face analysis and transformation features via AceDataCloud API. - Supports 7 specialized face APIs: keypoint detection, beautification, age change, gender swap, face swap, cartoon avatar creation, and liveness detection. - Each API works synchronously and returns results immediately. - Requires ACEDATACLOUD_API_TOKEN environment variable for authentication. - Detailed documentation included for each endpoint, parameters, and use cases. - Alpha stage release; interfaces and feature set may evolve.
元数据
Slug acedatacloud-face-transform
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Face Transform 是什么?

Analyze and transform faces via AceDataCloud API. Use when detecting face keypoints, beautifying portraits, aging/de-aging faces, swapping genders, replacing... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 123 次。

如何安装 Face Transform?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install acedatacloud-face-transform」即可一键安装,无需额外配置。

Face Transform 是免费的吗?

是的,Face Transform 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Face Transform 支持哪些平台?

Face Transform 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Face Transform?

由 Germey(@germey)开发并维护,当前版本 v1.0.0。

💬 留言讨论