> ## Documentation Index > Fetch the complete documentation index at: https://apidoc.cometapi.com/llms.txt > Use this file to discover all available pages before exploring further. # Opprett en Runway-karakteropptreden > Opprett en Runway Act-Two-oppgave for karakteropptreden via CometAPI ved å bruke et karakterbilde eller en video og et referanseklipp med opptreden. Bruk `act_two` til å overføre opptredenen fra en referansevideo til et karakterbilde eller en video. Forespørselen returnerer en oppgave-`id` for å hente det ferdige resultatet. ## Forbered ressursene * Autentiser med CometAPI API-nøkkelen din. * Angi `model` til `act_two`. * Oppgi `character.type` som `image` eller `video`, med ressursen i `character.uri`. Sørg for at et gjenkjennelig ansikt er synlig og innenfor rammen. * Oppgi `reference.type` som `video`, med et opptredensklipp på 3 til 30 sekunder i `reference.uri`. * Erstatt eksempel-URL-ene for medier med tilgjengelige HTTPS-URL-er. Mediefeltene godtar også Base64-data-URI-er med en kodet størrelse på opptil 5 MB. ## Konfigurer opptredenen Bare `model`, `character` og `reference` er påkrevd. | Felt | Slik bruker du det | | ----------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------- | | `bodyControl` | Angi `true` for å be om kroppsbevegelser og gester i tillegg til ansiktsuttrykk. Utelat for å la innstillingen være uspesifisert. | | `expressionIntensity` | Bruk `1` til `5`; høyere verdier ber om sterkere uttrykk. Utelat for `3`. | | `seed` | Bruk `1` til `4294967295` for en eksplisitt sampling seed. Utelat for en tilfeldig seed. | | `contentModeration.publicFigureThreshold` | Bruk `auto` for standard deteksjon av offentlige personer eller `low` for mindre restriktiv deteksjon. | `bodyControl: false` behandles som utelatelse, så det eksplisitt ikke deaktiverer kroppskontroll. En `seed` eller `expressionIntensity` med verdien `0` behandles også som utelatelse. Utelat valgfrie felt i stedet for å sende `null`. Valgfrie verdier for `ratio` er `1280:720`, `720:1280`, `960:960`, `1104:832`, `832:1104`, eller `1584:672`. ## Hent resultatet Lagre den returnerte `id` og bruk [Hent en Runway-oppgave](./runway-to-get-task-details) for å hente oppgavestatusen. Når `status` er `SUCCEEDED`, leser du resultat-URL-ene fra `output`. Hvis oppgaven mislykkes, undersøker du `failure` og `failureCode` når de finnes. ## OpenAPI ````yaml api/openapi/video/runway/official-format/post-control-a-character.openapi.json POST /runwayml/v1/character_performance openapi: 3.1.0 info: title: Create a Runway character performance version: 1.0.0 description: Create an asynchronous Runway task through CometAPI. servers: - url: https://api.cometapi.com security: - bearerAuth: [] paths: /runwayml/v1/character_performance: post: summary: Create a Runway character performance description: >- Submit the request and save the returned id. Retrieve task details to read the status and output URLs. operationId: control_a_character requestBody: required: true content: application/json: schema: type: object description: Act-Two character-performance request. properties: model: type: string description: Model ID for this request. enum: - act_two character: description: >- Character image or video to animate. Keep a recognizable face visible and inside the frame. oneOf: - type: object description: Character image to animate. properties: type: type: string description: Media type of the character asset. enum: - image uri: description: >- Character asset. Keep a recognizable face visible and inside the frame. Use an accessible HTTPS URL or a Base64 data URI with an encoded size of up to 5 MB. oneOf: - type: string description: Accessible HTTPS URL of the image. pattern: ^https:// maxLength: 2048 minLength: 13 - type: string description: >- Base64-encoded image, including its data URI prefix. pattern: ^data:image/[^;]+;base64, maxLength: 5242880 minLength: 13 required: - type - uri additionalProperties: false - type: object description: Character video to animate. properties: type: type: string description: Media type of the character asset. enum: - video uri: description: >- Character asset. Keep a recognizable face visible and inside the frame. Use an accessible HTTPS URL or a Base64 data URI with an encoded size of up to 5 MB. oneOf: - type: string description: Accessible HTTPS URL of the video. pattern: ^https:// maxLength: 2048 minLength: 13 - type: string description: >- Base64-encoded video, including its data URI prefix. pattern: ^data:video/[^;]+;base64, maxLength: 5242880 minLength: 13 required: - type - uri additionalProperties: false reference: type: object description: >- Reference video containing the performance to apply. The video must be 3 to 30 seconds long. properties: type: type: string description: Media type of the performance reference. enum: - video uri: description: >- Performance reference video, 3 to 30 seconds long. Use an accessible HTTPS URL or a Base64 data URI with an encoded size of up to 5 MB. oneOf: - type: string description: Accessible HTTPS URL of the video. pattern: ^https:// maxLength: 2048 minLength: 13 - type: string description: Base64-encoded video, including its data URI prefix. pattern: ^data:video/[^;]+;base64, maxLength: 5242880 minLength: 13 required: - type - uri additionalProperties: false bodyControl: type: boolean description: >- Set true to request body movements and gestures in addition to facial expressions. Omit to leave this option unspecified; false is treated as omission. expressionIntensity: type: integer description: >- Expression intensity from 1 through 5. Higher values request stronger expressions. Omit for 3; 0 is treated as omission. minimum: 0 maximum: 5 seed: type: integer description: >- Sampling seed. Omit for a random seed; 0 is treated as omission. minimum: 0 maximum: 4294967295 ratio: type: string description: Optional requested frame dimensions. enum: - '1280:720' - '720:1280' - '960:960' - '1104:832' - '832:1104' - '1584:672' contentModeration: type: object description: >- Content moderation settings. Omit to use the standard settings. properties: publicFigureThreshold: type: string description: >- Public-figure detection threshold. Use auto for standard detection or low for less restrictive detection. enum: - auto - low required: - publicFigureThreshold additionalProperties: false required: - model - character - reference additionalProperties: false example: model: act_two character: type: image uri: https://example.com/character.jpg reference: type: video uri: https://example.com/performance.mp4 bodyControl: true expressionIntensity: 3 responses: '200': description: The task was created. Save its id for task retrieval. content: application/json: schema: type: object properties: id: type: string description: Task ID for GET /runwayml/v1/tasks/{id}. status: type: string description: Task state, when returned. createdAt: type: string description: Task submission timestamp, when returned. format: date-time output: type: array description: Result URLs, when returned. items: type: string format: uri failure: type: string description: Failure explanation, when returned. failureCode: type: string description: Machine-readable failure code, when returned. estimatedCost: type: object description: Task estimate metadata, when returned. properties: credits: type: integer description: Credit value reported with the task. required: - credits additionalProperties: false cost: type: object description: Task cost metadata, when returned. properties: credits: type: integer description: Credit value reported with the task. required: - credits additionalProperties: false required: - id additionalProperties: false example: id: 00000000-0000-4000-8000-000000000000 '400': description: Invalid request or unavailable task ID. content: application/json: schema: oneOf: - type: object description: Task request error. properties: code: type: - string - integer description: Machine-readable task error code. message: type: string description: Error explanation. data: description: Additional error details, when returned. required: - code - message additionalProperties: true - type: object description: Request authentication or validation error. properties: error: type: object description: Error details. properties: message: type: string description: Error explanation. type: type: string description: Error category. code: type: - string - integer - 'null' description: Error code, when returned. required: - message additionalProperties: true required: - error additionalProperties: true '401': description: Authentication failed. content: application/json: schema: type: object description: Request authentication or validation error. properties: error: type: object description: Error details. properties: message: type: string description: Error explanation. type: type: string description: Error category. code: type: - string - integer - 'null' description: Error code, when returned. required: - message additionalProperties: true required: - error additionalProperties: true x-codeSamples: - lang: Shell source: |- curl --request POST \ --url https://api.cometapi.com/runwayml/v1/character_performance \ --header "Authorization: Bearer $COMETAPI_KEY" \ --header "Content-Type: application/json" \ --data '{ "model": "act_two", "character": { "type": "image", "uri": "https://example.com/character.jpg" }, "reference": { "type": "video", "uri": "https://example.com/performance.mp4" }, "bodyControl": true, "expressionIntensity": 3 }' - lang: Python source: |- import os import requests response = requests.post( "https://api.cometapi.com/runwayml/v1/character_performance", headers={"Authorization": f"Bearer {os.environ['COMETAPI_KEY']}"}, json={ "model": "act_two", "character": { "type": "image", "uri": "https://example.com/character.jpg" }, "reference": { "type": "video", "uri": "https://example.com/performance.mp4" }, "bodyControl": True, "expressionIntensity": 3 }, ) response.raise_for_status() print(response.json()) - lang: JavaScript source: |- const response = await fetch( "https://api.cometapi.com/runwayml/v1/character_performance", { method: "POST", headers: { Authorization: `Bearer ${process.env.COMETAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "act_two", "character": { "type": "image", "uri": "https://example.com/character.jpg" }, "reference": { "type": "video", "uri": "https://example.com/performance.mp4" }, "bodyControl": true, "expressionIntensity": 3 }), }, ); if (!response.ok) throw new Error(await response.text()); console.log(await response.json()); components: securitySchemes: bearerAuth: type: http scheme: bearer description: Your CometAPI API key. ````