← 返回 Skills 市场

Higgsfield Soul ID

Name: Higgsfield Soul ID
Author: higgsfield

作者 Yerzat Dulat · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ⚠ suspicious

总下载

当前安装

版本数

在 OpenClaw 中安装

/install higgsfield-soul-id

功能描述

Train a Soul Character — a personalized model on a person's face that Higgsfield uses for identity-faithful image and video generation. Use when: "create my...

使用说明 (SKILL.md)

Higgsfield Soul Character

Train a face-faithful identity model. Reusable across all Soul-powered generations.

Step 0 — Bootstrap

Before any other command:

If higgsfield is not on $PATH, install it:

curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh

If higgsfield account status fails with Session expired / Not authenticated, ask the user to run higgsfield auth login (interactive) and wait for confirmation.
Soul training requires a paid plan (Basic+). If higgsfield account status shows free plan, tell the user before submitting.

UX Rules

Be concise. No raw IDs in chat. Just say "Soul ready" with a name reference.
Detect language and respond in it. CLI flags stay English.
Ask for the smallest set of inputs: name + photos. Pick a sensible model variant.
Polling is silent — training takes minutes. Don't repeat status updates.

Workflow

Get name. One word, used for later reference. Ask if missing.
Get photos. 5–20 face photos, varied angles and lighting. Local paths or already-uploaded IDs both work — --image accepts either.
Pick variant.
- --soul-2 — for image generation (default)
- --soul-cinematic — for cinematic / video work Choose based on user's stated downstream use. Default to --soul-2.

Submit.

higgsfield soul-id create --name "\x3Cname>" --soul-2 --image ./photo1.png --image ./photo2.png ...
higgsfield soul-id create --name "\x3Cname>" --soul-2 --image \x3Cupload_id> --image \x3Cupload_id> ...

CLI auto-uploads paths. Captures returned reference id.

Wait. higgsfield soul-id wait \x3Cid>. Silent. Default timeout 30m.
Deliver. "Soul \x3Cname> ready. Use in generate with --soul-id \x3Cid>."

Use the Soul

Once trained, pass to higgsfield-generate:

higgsfield generate create text2image_soul_v2 --prompt "..." --soul-id \x3Cref_id> --wait
higgsfield generate create soul_cinema_studio --prompt "..." --soul-id \x3Cref_id> --wait

Listing existing Souls

higgsfield soul-id list                   # all references
higgsfield soul-id get \x3Cid>               # one by id

Errors

Minimum Basic plan required — user is on free plan; tell them.
Training failed — check photos quality (5+ unique faces, well-lit).
Session expired → higgsfield auth login.

Reference docs

references/photo-guide.md — what photos work best
references/troubleshooting.md — common training failures

安全使用建议

Install only if you are comfortable uploading the selected face photos to Higgsfield and creating a reusable identity model. Review or manually install the Higgsfield CLI instead of blindly running the curl-to-shell installer, confirm the account and any paid-plan implications, use only photos you have consent to use, and keep the resulting Soul ID private.

功能分析

Type: OpenClaw Skill Name: higgsfield-soul-id Version: 1.0.0 The skill bundle uses a high-risk 'curl | sh' pattern in SKILL.md to install a CLI tool from a remote GitHub repository (higgsfield-ai/cli). While this behavior is common in developer tools, it constitutes an unverified remote code execution risk within the agent's environment. There is no evidence of intentional malice, but the combination of shell access, remote script execution, and the handling of authentication tokens makes it a significant security concern.

能力评估

ℹ Purpose & Capability

The instructions coherently match the stated purpose of training a Higgsfield Soul identity model from user-provided photos, but the core capability involves biometric face data.

⚠ Instruction Scope

The workflow proceeds from collecting photos to running the create command that auto-uploads local paths, without an explicit final confirmation, consent check, retention guidance, or deletion guidance.

⚠ Install Mechanism

Although no install spec is declared, SKILL.md instructs the agent to install the Higgsfield CLI by piping a remote GitHub script directly to sh if the CLI is missing.

ℹ Credentials

Bash and a provider CLI are expected for this integration, but they give the skill broad local command execution and network-upload capability.

⚠ Persistence & Privilege

The skill uses an authenticated Higgsfield account, requires a paid plan, and creates a reusable identity model/reference that can be used in future image or video generations.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install higgsfield-soul-id
安装完成后，直接呼叫该 Skill 的名称或使用 /higgsfield-soul-id 触发
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 enabling personalized Soul Character training for identity-faithful image and video generation. - Allows users to train a reusable Soul model from a set of face photos. - Supports selection of image or cinematic model variant based on downstream use. - Streamlined onboarding: prompts for name, checks account status, and manages photo uploads. - Enforces clear, minimal chat prompts and silent progress polling. - Guides users on using trained Souls with other Higgsfield tools. - Handles common errors such as missing plan, photo issues, or authentication problems.

元数据

Slug higgsfield-soul-id

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