API-Referenz
OmniHuman Subjekterkennung
Verwenden Sie den Endpunkt „Subjekterkennung", um einen asynchronen Task zu erstellen.
01
Übersicht
Verwenden Sie den Endpunkt „Subjekterkennung" mit einem unterstützten Modell. Verwenden Sie die zurückgegebene Task-ID, um den Status abzurufen, oder geben Sie callback_url für die unten dokumentierten Zustellungen an.
Schnellstart
- Erstellen Sie einen API-Schlüssel und setzen Sie ihn als RUNAPI_API_KEY.
- Wählen Sie ein unterstütztes Modell und senden Sie eine POST-Anfrage, deren Body dem Schema dieses Modells entspricht.
- Speichern Sie die zurückgegebene Task-ID und fragen Sie den Status ab, bis ein Endzustand erreicht ist, oder verarbeiten Sie die unten dokumentierten Callbacks.
Endpunkt
- Basis-URL
https://runapi.ai- API-Version
v1- Authentifizierung
Authorization: Bearer YOUR_API_TOKEN
02
Unterstützte Modelle
Öffnen Sie eine Modellseite für aktuelle Preise, Ratenlimits und Details zur kommerziellen Nutzung.
03
JSON-BodyAnfrage-Schema
Felder und zulässige Werte hängen vom ausgewählten Modell ab. Wenn angegeben, empfängt callback_url die unten dokumentierten Task-Zustellungen.
omnihuman-1.5-subject-detection3 Felder
callback_urlstring
Optional
modelstring
Optional
source_image_urlstring
Erforderlich
04
HTTP 202Annahme erstellen
POST /api/v1/omnihuman/subject_detection
Antwort-Schema
JSON
{
"properties": {
"billing": {
"properties": {
"refund": {
"oneOf": [
{
"properties": {
"refunded_at": {
"type": "string"
}
},
"required": [
"refunded_at"
],
"type": "object",
"unevaluatedProperties": false
},
{
"enum": [
null
]
}
]
},
"reservation": {
"oneOf": [
{
"properties": {
"amount_cents": {
"type": "integer"
}
},
"required": [
"amount_cents"
],
"type": "object",
"unevaluatedProperties": false
},
{
"enum": [
null
]
}
]
},
"settlement": {
"oneOf": [
{
"properties": {
"amount_micro_cents": {
"type": "integer"
},
"charged_amount_cents": {
"type": "integer"
}
},
"required": [
"charged_amount_cents",
"amount_micro_cents"
],
"type": "object",
"unevaluatedProperties": false
},
{
"enum": [
null
]
}
]
}
},
"required": [
"reservation",
"settlement",
"refund"
],
"type": "object",
"unevaluatedProperties": false
},
"id": {
"type": "string"
},
"status": {
"enum": [
"processing"
],
"type": "string"
},
"task_replayed": {
"type": "boolean"
}
},
"required": [
"id",
"status",
"billing"
],
"type": "object",
"unevaluatedProperties": false
}Antwortbeispiel
JSON
{
"billing": {
"refund": null,
"reservation": null,
"settlement": null
},
"id": "tsk_reference_demo",
"status": "processing"
}05
HTTP 200Abfrage wird verarbeitet
GET /api/v1/omnihuman/subject_detection/:id
Antwort-Schema
JSON
{
"properties": {
"billing": {
"properties": {
"refund": {
"oneOf": [
{
"properties": {
"refunded_at": {
"type": "string"
}
},
"required": [
"refunded_at"
],
"type": "object",
"unevaluatedProperties": false
},
{
"enum": [
null
]
}
]
},
"reservation": {
"oneOf": [
{
"properties": {
"amount_cents": {
"type": "integer"
}
},
"required": [
"amount_cents"
],
"type": "object",
"unevaluatedProperties": false
},
{
"enum": [
null
]
}
]
},
"settlement": {
"oneOf": [
{
"properties": {
"amount_micro_cents": {
"type": "integer"
},
"charged_amount_cents": {
"type": "integer"
}
},
"required": [
"charged_amount_cents",
"amount_micro_cents"
],
"type": "object",
"unevaluatedProperties": false
},
{
"enum": [
null
]
}
]
}
},
"required": [
"reservation",
"settlement",
"refund"
],
"type": "object",
"unevaluatedProperties": false
},
"id": {
"type": "string"
},
"status": {
"enum": [
"processing"
],
"type": "string"
}
},
"required": [
"id",
"status",
"billing"
],
"type": "object",
"unevaluatedProperties": false
}Antwortbeispiel
JSON
{
"billing": {
"refund": null,
"reservation": null,
"settlement": null
},
"id": "tsk_reference_demo",
"status": "processing"
}06
HTTP 200Abfrage abgeschlossen
GET /api/v1/omnihuman/subject_detection/:id
Antwort-Schema
JSON
{
"properties": {
"billing": {
"properties": {
"refund": {
"oneOf": [
{
"properties": {
"refunded_at": {
"type": "string"
}
},
"required": [
"refunded_at"
],
"type": "object",
"unevaluatedProperties": false
},
{
"enum": [
null
]
}
]
},
"reservation": {
"oneOf": [
{
"properties": {
"amount_cents": {
"type": "integer"
}
},
"required": [
"amount_cents"
],
"type": "object",
"unevaluatedProperties": false
},
{
"enum": [
null
]
}
]
},
"settlement": {
"oneOf": [
{
"properties": {
"amount_micro_cents": {
"type": "integer"
},
"charged_amount_cents": {
"type": "integer"
}
},
"required": [
"charged_amount_cents",
"amount_micro_cents"
],
"type": "object",
"unevaluatedProperties": false
},
{
"enum": [
null
]
}
]
}
},
"required": [
"reservation",
"settlement",
"refund"
],
"type": "object",
"unevaluatedProperties": false
},
"id": {
"type": "string"
},
"masks": {
"items": {
"properties": {
"url": {
"type": "string",
"x-runapi-generated-media": true
}
},
"required": [
"url"
],
"type": "object",
"unevaluatedProperties": false
},
"type": "array"
},
"status": {
"enum": [
"completed"
],
"type": "string"
}
},
"required": [
"id",
"status",
"masks",
"billing"
],
"type": "object",
"unevaluatedProperties": false
}Antwortbeispiel
JSON
{
"billing": {
"refund": null,
"reservation": null,
"settlement": null
},
"id": "tsk_reference_demo",
"masks": [
{
"url": "https://file.runapi.ai/reference-mask.png"
}
],
"status": "completed"
}07
HTTP 200Abfrage fehlgeschlagen
GET /api/v1/omnihuman/subject_detection/:id
Antwort-Schema
JSON
{
"properties": {
"billing": {
"properties": {
"refund": {
"oneOf": [
{
"properties": {
"refunded_at": {
"type": "string"
}
},
"required": [
"refunded_at"
],
"type": "object",
"unevaluatedProperties": false
},
{
"enum": [
null
]
}
]
},
"reservation": {
"oneOf": [
{
"properties": {
"amount_cents": {
"type": "integer"
}
},
"required": [
"amount_cents"
],
"type": "object",
"unevaluatedProperties": false
},
{
"enum": [
null
]
}
]
},
"settlement": {
"oneOf": [
{
"properties": {
"amount_micro_cents": {
"type": "integer"
},
"charged_amount_cents": {
"type": "integer"
}
},
"required": [
"charged_amount_cents",
"amount_micro_cents"
],
"type": "object",
"unevaluatedProperties": false
},
{
"enum": [
null
]
}
]
}
},
"required": [
"reservation",
"settlement",
"refund"
],
"type": "object",
"unevaluatedProperties": false
},
"error": {
"type": "string"
},
"id": {
"type": "string"
},
"status": {
"enum": [
"failed"
],
"type": "string"
}
},
"required": [
"id",
"status",
"error",
"billing"
],
"type": "object",
"unevaluatedProperties": false
}Antwortbeispiel
JSON
{
"billing": {
"refund": null,
"reservation": null,
"settlement": null
},
"error": "Task processing failed.",
"id": "tsk_reference_demo",
"status": "failed"
}08
HTTP 200Kunden-Callback: abgeschlossen
POST callback_url
Antwort-Schema
JSON
{
"properties": {
"id": {
"type": "string"
},
"masks": {
"items": {
"properties": {
"url": {
"type": "string",
"x-runapi-generated-media": true
}
},
"required": [
"url"
],
"type": "object",
"unevaluatedProperties": false
},
"type": "array"
},
"status": {
"enum": [
"completed"
],
"type": "string"
}
},
"required": [
"id",
"status",
"masks"
],
"type": "object",
"unevaluatedProperties": false
}Antwortbeispiel
JSON
{
"id": "tsk_reference_demo",
"masks": [
{
"url": "https://file.runapi.ai/reference-mask.png"
}
],
"status": "completed"
}09
HTTP 200Kunden-Callback: fehlgeschlagen
POST callback_url
Antwort-Schema
JSON
{
"properties": {
"error": {
"oneOf": [
{
"type": "string"
},
{
"properties": {
"code": {
"type": "string"
},
"limit_cents": {
"type": "integer"
},
"message": {
"type": "string"
},
"reset_at": {
"format": "date-time",
"type": [
"string",
"null"
]
},
"used_cents": {
"type": "integer"
},
"window": {
"enum": [
"1h",
"1d",
"7d",
"daily",
"weekly",
"monthly",
"lifetime"
],
"type": "string"
}
},
"required": [
"code",
"message"
],
"type": "object",
"unevaluatedProperties": false
}
]
},
"id": {
"type": "string"
},
"status": {
"enum": [
"failed"
],
"type": "string"
}
},
"required": [
"id",
"status",
"error"
],
"type": "object",
"unevaluatedProperties": false
}Antwortbeispiel
JSON
{
"error": {
"code": "generation_failed",
"message": "Task processing failed."
},
"id": "tsk_reference_demo",
"status": "failed"
}10
HTTP 401Fehler
POST /api/v1/omnihuman/subject_detection
Antwort-Schema
JSON
{
"properties": {
"error": {
"description": "Für Menschen lesbare Fehlermeldung.",
"type": "string"
}
},
"required": [
"error"
],
"type": "object",
"unevaluatedProperties": false
}Antwortbeispiel
JSON
{
"error": "Authentication required"
}11
HTTP 401Fehler
GET /api/v1/omnihuman/subject_detection/:id
Antwort-Schema
JSON
{
"properties": {
"error": {
"description": "Für Menschen lesbare Fehlermeldung.",
"type": "string"
}
},
"required": [
"error"
],
"type": "object",
"unevaluatedProperties": false
}Antwortbeispiel
JSON
{
"error": "Authentication required"
}12
HTTP 400Fehler
POST /api/v1/omnihuman/subject_detection
Antwort-Schema
JSON
{
"oneOf": [
{
"properties": {
"error": {
"description": "Für Menschen lesbare Fehlermeldung.",
"type": "string"
}
},
"required": [
"error"
],
"type": "object",
"unevaluatedProperties": false
},
{
"properties": {
"error": {
"description": "Menschenlesbare Validierungszusammenfassung.",
"type": "string"
},
"errors": {
"additionalProperties": {
"items": {
"type": "string"
},
"type": "array"
},
"description": "Validierungsmeldungen nach öffentlichem Anforderungsfeld gegliedert, mit einem Array menschenlesbarer Zeichenketten für jedes Feld.",
"type": "object"
}
},
"required": [
"error",
"errors"
],
"type": "object",
"unevaluatedProperties": false
}
]
}Antwortbeispiel
JSON
{
"error": "model must be one of: omnihuman-1.5-subject-detection"
}13
HTTP 402Fehler
POST /api/v1/omnihuman/subject_detection
Antwort-Schema
JSON
{
"properties": {
"error": {
"description": "Für Menschen lesbare Fehlermeldung.",
"type": "string"
}
},
"required": [
"error"
],
"type": "object",
"unevaluatedProperties": false
}Antwortbeispiel
JSON
{
"error": "Insufficient balance"
}14
HTTP 429Fehler
POST /api/v1/omnihuman/subject_detection
Antwort-Schema
JSON
{
"properties": {
"error": {
"description": "Für Menschen lesbare Fehlermeldung.",
"type": "string"
}
},
"required": [
"error"
],
"type": "object",
"unevaluatedProperties": false
}Antwortbeispiel
JSON
{
"error": "API key credit limit exceeded"
}15
HTTP 409Fehler
POST /api/v1/omnihuman/subject_detection
Antwort-Schema
JSON
{
"properties": {
"error": {
"description": "Für Menschen lesbare Fehlermeldung.",
"type": "string"
}
},
"required": [
"error"
],
"type": "object",
"unevaluatedProperties": false
}Antwortbeispiel
JSON
{
"error": "The request uses features that are not supported for the selected model"
}16
HTTP 429Fehler
POST /api/v1/omnihuman/subject_detection
Antwort-Schema
JSON
{
"properties": {
"error": {
"description": "Für Menschen lesbare Fehlermeldung.",
"type": "string"
}
},
"required": [
"error"
],
"type": "object",
"unevaluatedProperties": false
}Antwortbeispiel
JSON
{
"error": "Rate limit reached. Please retry later."
}17
HTTP 503Fehler
POST /api/v1/omnihuman/subject_detection
Antwort-Schema
JSON
{
"properties": {
"error": {
"description": "Für Menschen lesbare Fehlermeldung.",
"type": "string"
}
},
"required": [
"error"
],
"type": "object",
"unevaluatedProperties": false
}Antwortbeispiel
JSON
{
"error": "Service under maintenance, please try again later"
}18
HTTP 504Fehler
POST /api/v1/omnihuman/subject_detection
Antwort-Schema
JSON
{
"properties": {
"error": {
"description": "Für Menschen lesbare Fehlermeldung.",
"type": "string"
}
},
"required": [
"error"
],
"type": "object",
"unevaluatedProperties": false
}Antwortbeispiel
JSON
{
"error": "The request timed out"
}19
HTTP 404Fehler
GET /api/v1/omnihuman/subject_detection/:id
Antwort-Schema
JSON
{
"properties": {
"error": {
"description": "Für Menschen lesbare Fehlermeldung.",
"type": "string"
}
},
"required": [
"error"
],
"type": "object",
"unevaluatedProperties": false
}Antwortbeispiel
JSON
{
"error": "Task with id 'tsk_reference_demo' not found"
}20
Generierte Code-Beispiele
Verwende cURL direkt oder installiere ein SDK für deine Programmiersprache. Jedes Beispiel übermittelt die in dieser Referenz gezeigte validierte Anfrage.
Installieren
Shell
pip install runapi-omnihuman
PYTHON
import os
from runapi.omnihuman import OmnihumanClient
client = OmnihumanClient(api_key=os.environ["RUNAPI_API_KEY"])
task = client.subject_detection.create(
model="omnihuman-1.5-subject-detection",
source_image_url="https://file.runapi.ai/portrait.png"
)