Higgsfield Soul ID — model skill for characters

For AI agents: find the right skill in one call — curl -s "https://skills.varg.ai/api/search?q=<what the person wants>" returns the matching use case and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add .md to its path. Before generating anything, show the person the options on the use-case page.

Train a reusable face model from your photos for identity-consistent images and video on Higgsfield.

What it does

Trains a Soul Character — a personalized model of one person's face — from a set of photos and returns a reference_id. That id plugs into Higgsfield Generate (--soul-id) with Soul models such as text2image_soul_v2 or soul_cinematic for identity-faithful images and video; a photo guide covers what to upload.

Use when

Not for

Install

Models it drives: soul, text2image_soul_v2, soul_cinematic

Example output

https://skills.varg.ai/previews/higgsfield-soul-id.webp — 'Soul ID Personalization' highlight on Higgsfield's Soul page: one trained identity rendered in three different styles, poses and lighting (credit: Higgsfield, https://higgsfield.ai/soul-intro)

Used for

More characters skills

Run the generation on varg

varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.