Skip to content
InfratoApp
InfratoApp / Resources / Agent skills / higgsfield-soul-id

higgsfield-soul-id

higgsfield-soul-id is the official agent skill of higgsfield published by higgsfield-ai, listed under images, audio & video. It lives in the higgsfield-ai/skills repository, which has 1,638 GitHub stars and is licensed under MIT; we last read it on 2026-10-08.

Trains a personalized Soul Character model based on a person's face for identity-faithful image and video generation. Requires a one-time training step to generate a reference_id, which is then used with higgsfield-generate for creating images or videos.

Official — higgsfield

Install

skills is a generic installer for any repository of Claude agent skills -- it reads higgsfield-ai/skills’s own structure rather than assuming one, the same way this page reads the skill’s own SKILL.md rather than assuming a format.

npx skills add higgsfield-ai/skills

What it connects to

Unverified means a mention in the skill’s own description, not a citation. A wrong claim here costs nothing to correct and nothing to trust yet.

Maintenance

Stars
1638
State
listed
Licence
MIT
From the repository

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).

higgsfield-soul-id compared with similar skills

higgsfield-soul-id compared with other skills for the same job, by publisher, what it does, repository stars and last update
SkillPublisherWhat it doesRepo starsLast update
higgsfield-soul-id (this page)higgsfield-aiTrain a Soul Character — a personalized model on a person's face that Higgsfield uses for identity-faithful i…1,6382026-09-26
higgsfield-brandkit(same repository)higgsfield-aiCreate and extend complete visual brand systems through the Higgsfield CLI and bundled deterministic local to…1,6382026-09-26
higgsfield-generate(same repository)higgsfield-aiGenerate images/videos/3D assets/audio via Higgsfield AI. Defaults: GPT Image 2.5 for image/design/text, Seed…1,6382026-09-26
higgsfield-marketplace-cards(same repository)higgsfield-aiGenerate marketplace product image cards through Higgsfield: compliant main image, secondary product images,…1,6382026-09-26
higgsfield-video-explainer(same repository)higgsfield-aiBuild a complete non-photoreal narrated explainer or story video from ordered 10-second blocks: one narrator,…1,6382026-09-26
higgsfield-youtube-thumbnail(same repository)higgsfield-aiCreate high-click-through YouTube thumbnails and vertical video covers through the Higgsfield CLI. Builds a t…1,6382026-09-26
transformers-jshuggingfaceUse Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Suppor…11,2132026-10-23

Skills from the same repository first, then others for this job by repository stars. Figures are from each repository when we last read it.

Common questions about higgsfield-soul-id

What does higgsfield-soul-id do?
Trains a personalized Soul Character model based on a person's face for identity-faithful image and video generation. Requires a one-time training step to generate a reference_id, which is then used with higgsfield-generate for creating images or videos.
How do I install higgsfield-soul-id?
Run npx skills add higgsfield-ai/skills. The skills installer reads the repository’s own structure, so it works for any repository of agent skills.
Who publishes higgsfield-soul-id?
higgsfield-ai. It is named as the official skill of higgsfield.
Is higgsfield-soul-id maintained, and what licence does it use?
Its repository has 1,638 GitHub stars and its state in our directory is listed. Its last commit we recorded was on 2026-09-26. The repository declares the MIT licence.

More agent skills for images, audio & video

All images, audio & video entries →

Learn this on Infrato