Train Higgsfield Soul Characters
Creating consistent AI images or videos of the same person is difficult with one-off prompts. This skill guides Higgsfield Soul training from consented photos and returns a reusable identity reference.
Do not auto-install this skill.
The canonical policy requires operator review before any installation action.
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "higgsfield-soul-id" from https://skillstore.io/skills/higgsfield-ai-higgsfield-soul-id.md and its manifest at https://skillstore.io/api/skills/higgsfield-ai-higgsfield-soul-id/manifest. Verify the artifact. Do not auto-install. Inspect the skill and report your findings, then wait for an operator or manual installation decision.Your Agent should still show its plan and request any confirmation required by the security policy.
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Using "higgsfield-soul-id". Train a Soul called Maya from these approved portraits.
Expected outcome:
Maya is ready. The identity reference is available for reuse in Higgsfield image workflows.
Using "higgsfield-soul-id". The training failed.
Expected outcome:
Using "higgsfield-soul-id". I want video results.
Expected outcome:
The cinematic Soul variant is selected because the target output is video. Training will continue after confirming the photo set.
The critical issue is the bootstrap command that pipes a remote GitHub installer directly into sh, enabling supply-chain code execution. Most static backtick and reconnaissance alerts are Markdown or visible CLI workflow false positives, but the skill still runs external Higgsfield commands. A semantic finding is included because the workflow auto-uploads biometric face photos through the CLI.
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
https://skillstore.io/skills/higgsfield-ai-higgsfield-soul-id/audits/6?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/higgsfield-ai-higgsfield-soul-id?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/higgsfield-ai-higgsfield-soul-id?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/higgsfield-ai-higgsfield-soul-id/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/higgsfield-ai-higgsfield-soul-id.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>higgsfield-ai. (2026). higgsfield-soul-id security audit report (audit version 6) [Author version 0.12.0]. Skillstore. https://skillstore.io/skills/higgsfield-ai-higgsfield-soul-id/audits/6@techreport{higgsfield-ai-higgsfield-ai-higgsfield-soul-id-2026,
author = {higgsfield-ai},
title = {higgsfield-soul-id security audit report (audit version 6)},
institution = {Skillstore},
year = {2026},
number = {6},
url = {https://skillstore.io/skills/higgsfield-ai-higgsfield-soul-id/audits/6},
note = {Author version 0.12.0}
}cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "higgsfield-soul-id security audit report (audit version 6)"
version: "0.12.0"
type: report
authors:
- name: "higgsfield-ai"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/higgsfield-ai-higgsfield-soul-id/audits/6"
identifiers:
- type: other
value: "skillstore:higgsfield-ai-higgsfield-soul-id:audit:6"
description: "Skillstore immutable audit report identifier"
Prepare a reusable face identity for consistent images across content campaigns.
Train a cinematic identity reference for recurring subjects in Higgsfield video workflows.
Build approved avatar references for prototypes, concepts, and brand-safe creative tests.
Train a Higgsfield Soul for me. Ask for the name and the face photos you need before starting.
Review my selected photo paths for Soul training readiness and tell me which files to replace before submission.
Create a cinematic Soul for this subject using these approved photos, then wait for training to finish.
Find my existing Higgsfield Soul reference for this subject and prepare a generation plan for image and video outputs.
Author
higgsfield-aiLicense
MIT
Author version
v0.12.0
Skillstore revision
r1
Ref
3e4b6c31a74a3bd1a291c98cf585d720cb9fbc88
Maintenance freshness
7/18/2026
Usage
1 downloads · 6 views
File structure
Create Product Photoshoots With Higgsfield
Product teams need campaign images in many formats without writing complex image prompts. This skill guides choices, calls Higgsfield, and returns finished image URLs.
Create Marketplace Product Image Sets
Marketplace listings need consistent images across main, secondary, and A+ placements. This skill routes product context to Higgsfield and returns labeled result links.
Generate Media with Higgsfield AI
Creative media production requires compatible models, inputs, and parameters. This skill routes requests through Higgsfield and returns media, 3D assets, audio, or video analysis.
Build Full-Stack Websites with Higgsfield
Building a production website requires design, infrastructure, security, and deployment decisions. This skill guides Claude or Codex through a structured Higgsfield CLI workflow.
Build Playable Browser Games with Higgsfield
Creating a coherent browser game requires coordinated design, assets, code, testing, and deployment. This skill guides that workflow through Higgsfield CLI and bundled asset tools.
Create Complete Visual Brand Systems
Brand creation often produces inconsistent assets and unclear approvals. This skill coordinates identity design, review stages, deterministic exports, and editable brandbooks.
Create Pose-Controlled Images and Videos
by doany-ai
Pose and motion control workflows can be hard to route across image and video models. This skill selects the right RunComfy path and prepares clear CLI guidance.
Generate and Edit AI Media with PonyFlash
by ponyflash
AI media work often spans separate generation, editing, and subtitle tools. PonyFlash combines SDK guidance with FFmpeg workflows for images, videos, speech, music, and exports.
Run RunComfy Models from the CLI
by runcomfy-com
Teams need a repeatable way to run RunComfy media models from scripts. This skill guides CLI install, authentication, model runs, polling, and downloads.
Create Consistent Video Storyboards
by supercmohq
Video concepts can lose continuity when clips are planned separately. This skill creates sequential storyboard sheets that preserve characters, products, settings, and visual states.
Create Reusable Photorealistic AI Actors
by supercmohq
Campaign teams need consistent fictional talent without supplying a person photograph. This skill creates one detailed adult identity that can guide later image and video generation.
Create and Edit Project Images
by openai
Producing consistent raster assets requires precise prompts, careful edits, and reliable output handling. This skill structures requests, creates or edits visuals, validates results, and saves project-ready files.