# Soul character of your face (/higgsfield-soul-id)

/higgsfield-soul-id is a Claude Code skill in the Brand & Content section. It is maintained by higgsfield-ai and published under the MIT license. Trains a Soul model from 5 to 20 face photos so generated images and videos keep that person's identity.

- Web version: https://skills.sgomez.dev/en/s/higgsfield-soul-id
- Section: [Brand & Content](https://skills.sgomez.dev/en/brand.md)
- Author: higgsfield-ai
- License: MIT
- Source: https://github.com/higgsfield-ai/skills/tree/f83af0bc1d937c8119099a11f8ebbf5e6fb99819/higgsfield-soul-id
- Updated 26 Sept 2026

## How to ask for it

- `Train a Soul on my face to use in videos`
- `I want a digital avatar that looks like me in generated images`
- `Create my digital twin for future video generations`

## Install

macOS · Linux:

```
curl -fsSL https://raw.githubusercontent.com/sgomez-dev/claude-skills/main/install.sh | bash
```

Windows:

```
irm https://raw.githubusercontent.com/sgomez-dev/claude-skills/main/install.ps1 | iex
```


## Author's 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).

- [How we review this](https://skills.sgomez.dev/en/methodology.md)