higgsfield-soul-id
Higgsfield Soul ID creates a reusable identity model trained on your face photos, enabling consistent self-representation across Higgsfield's image and video generation tools. Submit 5–20 photos with varied angles and lighting, then reference your trained Soul in downstream generation tasks using the returned ID.
Higgsfield Soul ID trains a personalized face model for identity-faithful image and video generation.
AI-generated summary based on this skill's SKILL.md
Install
higgsfield-ai/skills/higgsfield-soul-id · repository language: Python
git clone https://github.com/higgsfield-ai/skills
cp -r skills/higgsfield-soul-id ~/.claude/skills/higgsfield-soul-idFrequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What does Higgsfield Soul ID do?
Higgsfield Soul ID creates a reusable identity model trained on your face photos, enabling consistent self-representation across Higgsfield's image and video generation tools. Submit 5–20 photos with varied angles and lighting, then reference your trained Soul in downstream generation tasks using the returned ID.
How do I train my face for AI image generation with Soul ID?
Higgsfield Soul ID accepts 5–20 face photos with varied angles and lighting. Upload your selection, and the skill trains a personalized face model. Once training completes, you receive a Soul ID that you can reference in Higgsfield's image and video generation tasks to maintain identity-faithful output across multiple uses.
Can I create a digital twin of myself with Higgsfield Soul ID?
Yes. Higgsfield Soul ID builds a digital twin from your face photos for cinematic or photorealistic video creation. The trained Soul model preserves your appearance and can be reused across Higgsfield's generation tools, making it ideal for creating consistent avatars and identity-faithful videos.
What is a Soul character and how do I set one up?
A Soul character in Higgsfield Soul ID is your trained identity model—a reusable digital avatar derived from your face photos. Set one up by submitting 5–20 photos with varied angles and lighting; the skill trains your personalized model and returns a Soul ID you can use across multiple Higgsfield generation tasks.
How many photos do I need to create my Soul ID?
Higgsfield Soul ID requires 5–20 face photos. Vary angles, lighting, and expressions to help the model learn your appearance robustly. More diverse photos improve the quality and consistency of your trained identity model across downstream image and video generation.
Can I use my trained Soul across different Higgsfield tools?
Yes. Higgsfield Soul ID returns a Soul ID that is reusable across Higgsfield's image and video generation tools. Once trained, reference your Soul ID in any supported generation task to maintain consistent, identity-faithful output without retraining.
SKILL.md
rendered from the published skill — quoted content, verbatim
Higgsfield Soul Character
Train a face-faithful identity model. Reusable across all Soul-powered generations.
Step 0 — Bootstrap
Before any other command:
- If
higgsfieldis not on$PATH, install it:bash curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh - If
higgsfield account statusfails withSession expired/ `Not
(truncated - see the full file via the links below)
Read as markdown · JSON record · Browse the source repository
File tree — 3 files
higgsfield-soul-id/SKILL.md
higgsfield-soul-id/references/photo-guide.md
higgsfield-soul-id/references/troubleshooting.md