Trains a personalized face model (Soul Character) for identity-faithful image and video generation using the Higgsfield CLI.
How this skill is triggered — by the user, by Claude, or both
Slash command
/claude-skills-library:higgsfield-soul-id [name] [photo paths...][name] [photo paths...]This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Train a face-faithful identity model. Reusable across all Soul-powered generations.
Train a face-faithful identity model. Reusable across all Soul-powered generations.
Before any other command:
higgsfield is not on $PATH, install it:
curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh
higgsfield account status fails with Session expired / Not authenticated, ask the user to run higgsfield auth login (interactive) and wait for confirmation.higgsfield account status shows free plan, tell the user before submitting.--image accepts either.--soul-2 — for image generation (default)--soul-cinematic — for cinematic / video work
Choose based on user's stated downstream use. Default to --soul-2.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.higgsfield soul-id wait <id>. Silent. Default timeout 30m.<name> ready. Use in generate with --soul-id <id>."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
higgsfield soul-id list # all references
higgsfield soul-id get <id> # one by id
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.references/photo-guide.md — what photos work bestreferences/troubleshooting.md — common training failuresnpx claudepluginhub frankxai/claude-skills-library --plugin claude-skills-libraryGenerates talking photo videos from images and creates videos using Flyworks/HiFly digital human avatars with TTS or voice cloning.
Generates humanized, realistic images via Google AI Studio (Gemini) in influencer or educational styles with natural lighting and subtle imperfections. Activates on image generation requests.
Provides Runway ML public API reference: models, endpoints, costs, limits, types for video generation, image generation, audio, and characters.