higgsfield-soul-id

Use it when: you want your face, or someone's, to stay recognizable across images and videos made on Higgsfield, a platform hosting many AI image, video and audio models
It does: trains a "Soul", Higgsfield's personal model of one face, from 5 to 20 photos
You get: a Soul ID that the higgsfield-generate skill then uses to put that face in new images and videos
Needs: the higgsfield CLI and a paid Higgsfield plan

TLDR

A one-time step before generating images or videos of a real person. The agent asks for a one-word name and 5 to 20 photos of the face from varied angles and lighting, and trains the Soul for still images by default, or for cinematic shots and video if that's what you'll use it for. Training takes minutes; the agent waits without status chatter and tells you when the Soul is ready. From then on, higgsfield-generate can use it in any generation. It can also list the Souls you already have. You don't need it for a one-off face swap from a single photo, or for an invented character with no real face to learn: higgsfield-generate handles both directly.

Summarizes the skill at f83af0b. Its SKILL.md has changed by 2 words since.

npx skills add https://github.com/higgsfield-ai/skills --skill higgsfield-soul-id

skills.sh page · Source on GitHub · All skills from higgsfield-ai/skills

Installs: 153,598 on skills.sh, Sep 21, 2026
Repo stars: 1,078 higgsfield-ai/skills
First seen: May 4, 2026 on skills.sh

Weekly installs

9.2K

-16% over 8 weeks · week to Sep 21

Weekly values

Week to	Installs
Aug 3	10,904
Aug 10	9,529
Aug 17	7,943
Aug 24	7,967
Aug 31	8,296
Sep 7	7,982
Sep 14	10,667
Sep 21	9,177

Category	category:media Generate and edit video, images and audio.
Type	type:tool Operates a CLI, API, app or bundled script to get something done.
Effect	effect:remote Its own steps change something outside your machine: post, send, deploy, provision, file issues, drive a website, or upload data to a service.
Needs	needs:cli needs:account A specific command-line tool or desktop app must be installed, such as gh, agent-browser, LibreOffice, Obsidian or a vendor CLI. An account, API key or paid plan with an outside service.
Publisher	by:official A verified publisher on its registry (skills.sh, ClawHub or Tencent SkillHub), or the company or maintainer behind the product the skill operates.
Topics	image ai-generation
Stack	stack:higgsfield

SKILL.md

From higgsfield-ai/skills at 4d07574. Checked daily, last changed Oct 28, 2026.

Frontmatter

version: 0.14.0
name: higgsfield-soul-id
description: |
  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".
  Chain: train Soul (one-time, returns reference_id) → use in
  higgsfield-generate via `--soul-id <id>` with models like
  `text2image_soul_v2` or `soul_cinematic`.
  NOT for: one-shot face swaps (use higgsfield-generate with --image),
  named-character / non-photo avatars (use higgsfield-generate with prompt).
argument-hint: "[name] [photo paths...]"
allowed-tools: Bash

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 "<name>" --soul-2 --image ./photo1.png --image ./photo2.png ...
higgsfield soul-id create --name "<name>" --soul-2 --image <upload_id> --image <upload_id> ...

CLI auto-uploads paths. Captures returned reference id.

Wait. higgsfield soul-id wait <id>. Silent. Default timeout 30m.
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

--soul-id is sent as the model's custom_reference_id. For a curated Soul style, list styles with higgsfield preset list soul-v2 and pass the chosen id as --style_id on text2image_soul_v2. --style_id cannot be combined with --image.

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