SkillsAdd

higgsfield-ai/skills

higgsfield-soul-id

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 Soul", "train my face", "make my digital twin", "build me an avatar", "learn my appearance", "create a character of me", "set up identity for video", "I want my face in generated images". higgsfield-generate via `--soul-id <id>` with models like `text2image_soul_v2` or `soul_cinema_studio`. NOT for: one-shot face swaps (use higgsfield-gener…

All-time #287 Trending #207 Hot #6582 First seen May 4, 2026
8-week activity · all time api

Installation

$ npx skills add higgsfield-ai/skills --skill higgsfield-soul-id
View on skills.sh ↗ GitHub repository ↗

Summary

  • Train a reusable face identity model for personalized image and video generation.
  • Requires 5–20 face photos from varied angles and lighting; accepts local file paths or pre-uploaded image IDs Two model variants: --soul-2 for image generation (default) and --soul-cinematic for video work Returns a reference ID after training completes, then pass to higgsfield-generate with --soul-id flag to generate identity-faithful content Requires paid plan (Basic+) and authenticated session via higgsfield auth login

Stronger alternatives

Audit results are mixed — compare nearby options before installing.

higgsfield-generate Same source · more installs
higgsfield-ai/skills

Generate images/videos/3D assets/audio via Higgsfield AI. Defaults: GPT Image 2 for image/desig…

156.5K installs
higgsfield-product-photoshoot Same source · more installs
higgsfield-ai/skills

Generate brand-quality product images through Higgsfield product-photoshoot prompt enhancement …

137K installs
higgsfield-marketplace-cards Same source
higgsfield-ai/skills

Generate marketplace product image cards through Higgsfield: compliant main image, secondary pr…

134.4K installs
higgsfield-websites Same source
higgsfield-ai/skills

Build, edit, and deploy full-stack websites, apps and games via the Higgsfield CLI (`higgsfield…

76.3K installs

Security audits

Partner security reviews for this skill.

agent-trust-hub SAFE

Analyzed May 7, 2026

No security issues detected. The skill facilitates training personalized identity models using the official Higgsfield CLI. It includes a bootstrap step to install the vendor's tool from their official repository and follows standard practices for authentication and resource management.

snyk CRITICAL

Analyzed May 7, 2026

[CRITICAL] E005: Suspicious download URL detected in skill instructions. [MEDIUM] W012: Unverifiable external dependency detected (runtime URL that controls agent).

socket Score 0.9000 · 0 alerts

Analyzed May 7, 2026

  • license 1
  • maintenance 1
  • quality 0.9
  • supply chain 1
  • vulnerability 1

0 alerts

Also in this package

Other skills from higgsfield-ai/skills.

npx skills add higgsfield-ai/skills
higgsfield-generate 156.5K higgsfield-product-photoshoot 137K higgsfield-marketplace-cards 134.4K higgsfield-websites 76.3K higgsfield-video-explainer 64.6K higgsfield-youtube-thumbnail 42.8K higgsfield-brandkit 42.8K higgsfield-game-generation 26.7K higgsfield-soul 2

Browse all from higgsfield-ai/skills

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 902
License LICENSE
Default branch main
Status Active

Skill metadata

Parsed from SKILL.md frontmatter.

Version0.12.0
Allowed toolsBash

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 3,378 B
  • docs SUMMARY.md 682 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 137,009 installs

SKILL.md

Higgsfield Soul Character

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

Step 0 — Bootstrap

Before any other command:

  1. If higgsfield is not on $PATH, install it:

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

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

UX Rules

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

Workflow

  1. Get name. One word, used for later reference. Ask if missing.
  2. Get photos. 5–20 face photos, varied angles and lighting. Local paths or already-uploaded IDs both work — --image accepts either.
  3. 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.

  1. Submit.

``bash higgsfield soul-id create --name "<name>" --soul-2 --image ./photo1.png --image ./photo2.png ... higgsfield soul-id create --name "<name>" --soul-2 --image <uploadid> --image <uploadid> ... `` CLI auto-uploads paths. Captures returned reference id.

  1. Wait. higgsfield soul-id wait <id>. Silent. Default timeout 30m.
  2. Deliver. "Soul <name> ready. Use in generate with --soul-id <id>."

Use the Soul

Once trained, pass to higgsfield-generate:

higgsfield generate create text2image_soul_v2 --prompt "..." --soul-id <ref_id> --quality 2k --wait
higgsfield generate create soul_cinematic --prompt "..." --soul-id <ref_id> --quality 2k --wait

Listing existing Souls

higgsfield soul-id list                   # all references
higgsfield soul-id get <id>               # 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