---
id: daily-higgsfield-soul-id
name: "higgsfield-soul-id"
url: https://skills.yangsir.net/skill/daily-higgsfield-soul-id
author: higgsfield-ai
domain: multimedia
tags: ["generative-ai", "image-generation", "ai-agents", "personalization"]
install_count: 21500
rating: 4.60 (24 reviews)
github: https://github.com/higgsfield-ai/skills
---

# higgsfield-soul-id

> 训练个性化面部AI模型，保持人物身份一致性，跨场景复用生成，AI Agent Skill，提升工作效率和自动化能力

**Stats**: 21,500 installs · 4.6/5 (24 reviews)

## Before / After 对比

### 人物一致性生成

**Before**:

每次生成新内容时重新输入人物特征描述，导致AI生成的人物外观不一致，需要反复调整提示词和多次重试，浪费时间和Token

**After**:

一次性训练专属面部模型，在所有后续生成中自动保持人物身份一致性，无需重复描述特征，大幅提升生成效率和准确度

| Metric | Before | After | Change |
|---|---|---|---|
| 生成成功率 | 40% | 95% | +138% |

## Readme

# higgsfield-soul-id

# Higgsfield Soul Character

Train a face-faithful identity model. Reusable across all Soul-powered generations.

## Step 0 — Bootstrap

Before any other command:

- If `higgsfield` is not on `$PATH`, install it:

```
curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh

```

- If `higgsfield account status` fails with `Session expired` / `Not authenticated`, ask the user to run `higgsfield auth login` (interactive) and wait for confirmation.

- Soul training requires a paid plan (Basic+). If `higgsfield account status` shows 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 — `--image` accepts 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.**

```
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.

- **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> --wait
higgsfield generate create soul_cinema_studio --prompt "..." --soul-id <ref_id> --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 best

- `references/troubleshooting.md` — common training failures

Weekly Installs2.4KRepository[higgsfield-ai/skills](https://github.com/higgsfield-ai/skills)GitHub Stars45First Seen1 day agoSecurity Audits[Gen Agent Trust HubPass](/higgsfield-ai/skills/higgsfield-soul-id/security/agent-trust-hub)[SocketPass](/higgsfield-ai/skills/higgsfield-soul-id/security/socket)[SnykFail](/higgsfield-ai/skills/higgsfield-soul-id/security/snyk)

---
*Source: https://skills.yangsir.net/skill/daily-higgsfield-soul-id*
*Markdown mirror: https://skills.yangsir.net/api/skill/daily-higgsfield-soul-id/markdown*