Agent Skills
› AjayIrkal23/agentic-mercy-10x
› higgsfield-soul-id
higgsfield-soul-id
GitHub训练基于人脸的个性化身份模型（Soul），用于生成高保真图像和视频。适用于创建数字分身或角色，需付费计划，支持图片/视频生成调用。
触发场景
create my Soul
train my face
make my digital twin
build me an avatar
安装
npx skills add AjayIrkal23/agentic-mercy-10x --skill higgsfield-soul-id -g -y
SKILL.md
Frontmatter
{
"name": "higgsfield-soul-id",
"version": "0.7.0",
"description": "Train a Soul Character — a personalized model on a person's face that\nHiggsfield uses for identity-faithful image and video generation.\nUse when: \"create my Soul\", \"train my face\", \"make my digital twin\",\n\"build me an avatar\", \"learn my appearance\", \"create a character of me\",\n\"set up identity for video\", \"I want my face in generated images\".\nChain: train Soul (one-time, returns reference_id) → use in\nhiggsfield-generate via `--soul-id <id>` with models like\n`text2image_soul_v2` or `soul_cinema_studio`.\nNOT for: one-shot face swaps (use higgsfield-generate with --image),\nnamed-character \/ non-photo avatars (use higgsfield-generate with prompt).\n",
"allowed-tools": "Bash",
"argument-hint": "[name] [photo paths...]"
}
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:curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh - If
higgsfield account statusfails withSession expired/Not authenticated, ask the user to runhiggsfield auth login(interactive) and wait for confirmation. - Soul training requires a paid plan (Basic+). If
higgsfield account statusshows free plan, tell the user before submitting.
UX Rules
- Be concise. No raw IDs in chat. Just say "Soul ready" with a name reference.
- Detect language and respond in it. CLI flags stay English.
- Ask for the smallest set of inputs: name + photos. Pick a sensible model variant.
- Polling is silent — training takes minutes. Don't repeat status updates.
Workflow
- Get name. One word, used for later reference. Ask if missing.
- Get photos. 5–20 face photos, varied angles and lighting. Local paths or already-uploaded IDs both work —
--imageaccepts either. - Pick variant.
--soul-2— for image generation (default)--soul-cinematic— for cinematic / video work Choose based on user's stated downstream use. Default to--soul-2.
- Submit.
CLI auto-uploads paths. Captures returned reference id.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> ... - Wait.
higgsfield soul-id wait <id>. Silent. Default timeout 30m. - Deliver. "Soul
<name>ready. Use in generate with--soul-id <id>."
Use the Soul
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
Listing existing Souls
higgsfield soul-id list # all references
higgsfield soul-id get <id> # one by id
Errors
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.
Reference docs
references/photo-guide.md— what photos work bestreferences/troubleshooting.md— common training failures
版本历史
- 581d130 当前 2026-07-19 09:11
