> ## 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-oppgave for image-to-video > Animer et kildebilde med Gen-4.5 eller Gen-4 Turbo, og hent resultatet som en Runway-oppgave. Bruk dette endepunktet til å animere et kildebilde. Send CometAPI API-nøkkelen din med Bearer-autentisering og en JSON-forespørselstekst. ## Velg en modell | Modell | Obligatoriske felt | Prompt for bevegelse | | ------------ | --------------------------------------------------------- | ---------------------------------------------------------------------------------------- | | `gen4.5` | `model`, `promptImage`, `promptText`, `ratio`, `duration` | Beskriv bevegelsen i `promptText`. | | `gen4_turbo` | `model`, `promptImage`, `ratio` | Du kan eventuelt beskrive bevegelsen i `promptText`, med 1 til 1 000 UTF-16-kodeenheter. | For en forespørsel kun med tekst bruker du [Opprett en Runway-oppgave for text-to-video](./generate-a-video-from-text). ## Oppgi det første bildet Sett `promptImage` til en tilgjengelig HTTPS-bilde-URL eller en Base64-bildedata-URI. Du kan også oppgi en matrise med ett element som inneholder `uri` og `position: "first"`. Dette grensesnittet godtar én startramme; ikke legg til en oppføring for siste ramme. HTTPS-bilder må være direkte tilgjengelige uten omdirigeringer og ha gyldige innholdshoder for bilder. Kodede bildedata-URI-er kan være opptil 5 MB. Se [Krav til Runway-medieinndata](https://docs.dev.runwayml.com/assets/inputs/) for bildeformater og dimensjoner. ## Angi varighet og dimensjoner Bruk en heltallsverdi for `duration` fra `2` til og med `10` sekunder. Det er påkrevd for `gen4.5` og valgfritt for `gen4_turbo`. Sett `ratio` til `1280:720`, `720:1280`, `1104:832`, `960:960`, `832:1104` eller `1584:672`. Dette er bredde- og høydeverdier atskilt med kolon. For et eksplisitt sampling-seed bruker du `1` til og med `4294967295`. Utelatelse eller `0` velger et tilfeldig seed. Hvis du inkluderer `contentModeration`, må den tilhørende `publicFigureThreshold` settes til `auto` eller `low`; ellers utelater du objektet. ## Velg et utdataformat `gen4.5` godtar `outputFormat` for MP4, ProRes, PNG-sekvenser og HDR- formatene som er oppført i forespørselsskjemaet. Utelat feltet for H.264 MP4. `proresProfile` gjelder bare for `prores` og `hdr_prores`; de tillatte verdiene avhenger av det valgte formatet. Utelat begge feltene med `gen4_turbo`. ## Hent resultatet Lagre den returnerte `id` og bruk [Hent en Runway-oppgave](./runway-to-get-task-details). Når `status` er `SUCCEEDED`, leser du resultat-URL-ene i `output`. ## OpenAPI ````yaml api/openapi/video/runway/official-format/post-runway-images-raw-video.openapi.json POST /runwayml/v1/image_to_video openapi: 3.1.0 info: title: Create a Runway image-to-video task version: 1.0.0 description: Create a Runway image-to-video task through CometAPI. servers: - url: https://api.cometapi.com security: - bearerAuth: [] paths: /runwayml/v1/image_to_video: post: summary: Create a Runway image-to-video task description: >- Submit a JSON request and save the returned id. Use GET /runwayml/v1/tasks/{id} to retrieve the result. operationId: runway_images_raw_video requestBody: required: true content: application/json: schema: oneOf: - title: gen4.5 type: object properties: model: type: string description: Model ID for this request variant. const: gen4.5 enum: - gen4.5 promptText: description: >- Describe the requested scene or motion in 1 to 1,000 UTF-16 code units. type: string minLength: 1 maxLength: 1000 promptImage: description: >- Image to use as the first frame. Supply a media URI or a one-item array with position set to first. oneOf: - description: >- Source image as a public HTTPS URL or a Base64 image data URI. oneOf: - type: string description: >- Public HTTPS image URL. The server must allow HEAD and GET without redirects. pattern: ^https:// maxLength: 2048 - type: string description: >- Base64 image data URI, including its media type. Maximum encoded length: 5 MB. pattern: ^data:image/[^;]+;base64, maxLength: 5242880 - type: array title: First-frame array minItems: 1 maxItems: 1 items: type: object properties: uri: description: >- Source image as a public HTTPS URL or a Base64 image data URI. oneOf: - type: string description: >- Public HTTPS image URL. The server must allow HEAD and GET without redirects. pattern: ^https:// maxLength: 2048 - type: string description: >- Base64 image data URI, including its media type. Maximum encoded length: 5 MB. pattern: ^data:image/[^;]+;base64, maxLength: 5242880 position: type: string description: >- Frame position. Only the first frame is supported. enum: - first required: - uri - position additionalProperties: false seed: type: integer minimum: 0 maximum: 4294967295 description: >- Optional sampling seed. Use a positive integer for an explicit seed. Omission or 0 selects a random seed. ratio: description: >- Requested output dimensions, expressed as width:height. Choose a value listed for this model and endpoint. type: string enum: - '1280:720' - '720:1280' - '1104:832' - '960:960' - '832:1104' - '1584:672' duration: description: >- Requested video duration in whole seconds, from 2 through 10. type: integer minimum: 2 maximum: 10 contentModeration: type: object description: >- Optional content moderation settings. Omit the object to use standard moderation. properties: publicFigureThreshold: type: string description: >- Use auto for standard moderation or low for less restrictive public-figure filtering. enum: - auto - low required: - publicFigureThreshold additionalProperties: false outputFormat: description: >- Output encoding. Omit for mp4 (H.264). prores returns MOV; png_sequence returns a PNG ZIP; sdr_rec709_10bit returns 10-bit Rec.709 HEVC. hdr10 and hlg return 10-bit HDR MP4; hdr_pq_12bit_master returns 12-bit HEVC MOV; hdr_prores returns HDR ProRes MOV. The HDR PNG/EXR sequence formats return ZIP archives; the ACEScg variants target the named ACES version. type: string enum: - mp4 - prores - png_sequence - hdr10 - hlg - sdr_rec709_10bit - hdr_pq_12bit_master - hdr_prores - hdr_png_sequence - hdr_exr_sequence - hdr_exr_acescg_sequence_1_3 - hdr_exr_acescg_sequence_2_0 proresProfile: description: >- Profile for outputFormat prores or hdr_prores. Omit for 4444 with prores, or 422 HQ with hdr_prores. hdr_prores accepts only 422, 422 HQ, or 4444. Omit this field for other formats. type: string enum: - '422' - '4444' - 422 Proxy - 422 LT - 422 HQ - 4444 XQ required: - promptText - promptImage - ratio - duration - model allOf: - if: required: - proresProfile then: required: - outputFormat properties: outputFormat: type: string description: Output format when proresProfile is supplied. enum: - prores - hdr_prores - if: required: - outputFormat properties: outputFormat: const: hdr_prores description: HDR ProRes output. then: properties: proresProfile: type: string description: Profile supported by HDR ProRes. enum: - '422' - 422 HQ - '4444' additionalProperties: false description: Request parameters for gen4.5. - title: gen4_turbo type: object properties: model: type: string description: Model ID for this request variant. const: gen4_turbo enum: - gen4_turbo promptImage: description: >- Image to use as the first frame. Supply a media URI or a one-item array with position set to first. oneOf: - description: >- Source image as a public HTTPS URL or a Base64 image data URI. oneOf: - type: string description: >- Public HTTPS image URL. The server must allow HEAD and GET without redirects. pattern: ^https:// maxLength: 2048 - type: string description: >- Base64 image data URI, including its media type. Maximum encoded length: 5 MB. pattern: ^data:image/[^;]+;base64, maxLength: 5242880 - type: array title: First-frame array minItems: 1 maxItems: 1 items: type: object properties: uri: description: >- Source image as a public HTTPS URL or a Base64 image data URI. oneOf: - type: string description: >- Public HTTPS image URL. The server must allow HEAD and GET without redirects. pattern: ^https:// maxLength: 2048 - type: string description: >- Base64 image data URI, including its media type. Maximum encoded length: 5 MB. pattern: ^data:image/[^;]+;base64, maxLength: 5242880 position: type: string description: >- Frame position. Only the first frame is supported. enum: - first required: - uri - position additionalProperties: false seed: type: integer minimum: 0 maximum: 4294967295 description: >- Optional sampling seed. Use a positive integer for an explicit seed. Omission or 0 selects a random seed. ratio: description: >- Requested output dimensions, expressed as width:height. Choose a value listed for this model and endpoint. type: string enum: - '1280:720' - '720:1280' - '1104:832' - '832:1104' - '960:960' - '1584:672' duration: description: >- Requested video duration in whole seconds, from 2 through 10. type: integer minimum: 2 maximum: 10 contentModeration: type: object description: >- Optional content moderation settings. Omit the object to use standard moderation. properties: publicFigureThreshold: type: string description: >- Use auto for standard moderation or low for less restrictive public-figure filtering. enum: - auto - low required: - publicFigureThreshold additionalProperties: false promptText: description: >- Optional motion prompt, from 1 to 1,000 UTF-16 code units. type: string minLength: 1 maxLength: 1000 required: - promptImage - ratio - model additionalProperties: false description: Request parameters for gen4_turbo. discriminator: propertyName: model examples: Gen-4.5: summary: Gen-4.5 value: model: gen4.5 promptImage: >- https://upload.wikimedia.org/wikipedia/commons/3/3a/Cat03.jpg promptText: The cat turns toward the camera. ratio: '1280:720' duration: 5 Gen-4 Turbo: summary: Gen-4 Turbo value: model: gen4_turbo promptImage: >- https://upload.wikimedia.org/wikipedia/commons/3/3a/Cat03.jpg ratio: '1280:720' duration: 5 promptText: The cat turns toward the camera. First-frame array: summary: First-frame array value: model: gen4.5 promptImage: - uri: >- https://upload.wikimedia.org/wikipedia/commons/3/3a/Cat03.jpg position: first promptText: The cat turns toward the camera. ratio: '1280:720' duration: 5 responses: '200': description: Task submitted. Save its id to retrieve task status. 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: 00000000-0000-4000-8000-000000000001 '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 label: Gen-4.5 source: | curl "https://api.cometapi.com/runwayml/v1/image_to_video" \ --request POST \ --header "Authorization: Bearer $COMETAPI_KEY" \ --header "Content-Type: application/json" \ --data '{ "model": "gen4.5", "promptImage": "https://upload.wikimedia.org/wikipedia/commons/3/3a/Cat03.jpg", "promptText": "The cat turns toward the camera.", "ratio": "1280:720", "duration": 5 }' - lang: Python label: Gen-4.5 source: | import os import requests payload = {'model': 'gen4.5', 'promptImage': 'https://upload.wikimedia.org/wikipedia/commons/3/3a/Cat03.jpg', 'promptText': 'The cat turns toward the camera.', 'ratio': '1280:720', 'duration': 5} response = requests.post( "https://api.cometapi.com/runwayml/v1/image_to_video", headers={"Authorization": "Bearer " + os.environ["COMETAPI_KEY"]}, json=payload, timeout=60, ) response.raise_for_status() print(response.json()["id"]) - lang: JavaScript label: Gen-4.5 source: | const payload = { "model": "gen4.5", "promptImage": "https://upload.wikimedia.org/wikipedia/commons/3/3a/Cat03.jpg", "promptText": "The cat turns toward the camera.", "ratio": "1280:720", "duration": 5 }; const response = await fetch( "https://api.cometapi.com/runwayml/v1/image_to_video", { method: "POST", headers: { Authorization: `Bearer ${process.env.COMETAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify(payload), }, ); if (!response.ok) throw new Error(await response.text()); console.log((await response.json()).id); - lang: Shell label: Gen-4 Turbo source: | curl "https://api.cometapi.com/runwayml/v1/image_to_video" \ --request POST \ --header "Authorization: Bearer $COMETAPI_KEY" \ --header "Content-Type: application/json" \ --data '{ "model": "gen4_turbo", "promptText": "The cat turns toward the camera.", "promptImage": "https://upload.wikimedia.org/wikipedia/commons/3/3a/Cat03.jpg", "ratio": "1280:720", "duration": 5 }' - lang: Python label: Gen-4 Turbo source: | import os import requests payload = {'model': 'gen4_turbo', 'promptText': 'The cat turns toward the camera.', 'promptImage': 'https://upload.wikimedia.org/wikipedia/commons/3/3a/Cat03.jpg', 'ratio': '1280:720', 'duration': 5} response = requests.post( "https://api.cometapi.com/runwayml/v1/image_to_video", headers={"Authorization": "Bearer " + os.environ["COMETAPI_KEY"]}, json=payload, timeout=60, ) response.raise_for_status() print(response.json()["id"]) - lang: JavaScript label: Gen-4 Turbo source: | const payload = { "model": "gen4_turbo", "promptText": "The cat turns toward the camera.", "promptImage": "https://upload.wikimedia.org/wikipedia/commons/3/3a/Cat03.jpg", "ratio": "1280:720", "duration": 5 }; const response = await fetch( "https://api.cometapi.com/runwayml/v1/image_to_video", { method: "POST", headers: { Authorization: `Bearer ${process.env.COMETAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify(payload), }, ); if (!response.ok) throw new Error(await response.text()); console.log((await response.json()).id); - lang: Shell label: First-frame array source: | curl "https://api.cometapi.com/runwayml/v1/image_to_video" \ --request POST \ --header "Authorization: Bearer $COMETAPI_KEY" \ --header "Content-Type: application/json" \ --data '{ "model": "gen4.5", "promptImage": [ { "uri": "https://upload.wikimedia.org/wikipedia/commons/3/3a/Cat03.jpg", "position": "first" } ], "promptText": "The cat turns toward the camera.", "ratio": "1280:720", "duration": 5 }' - lang: Python label: First-frame array source: | import os import requests payload = {'model': 'gen4.5', 'promptImage': [{'uri': 'https://upload.wikimedia.org/wikipedia/commons/3/3a/Cat03.jpg', 'position': 'first'}], 'promptText': 'The cat turns toward the camera.', 'ratio': '1280:720', 'duration': 5} response = requests.post( "https://api.cometapi.com/runwayml/v1/image_to_video", headers={"Authorization": "Bearer " + os.environ["COMETAPI_KEY"]}, json=payload, timeout=60, ) response.raise_for_status() print(response.json()["id"]) - lang: JavaScript label: First-frame array source: | const payload = { "model": "gen4.5", "promptImage": [ { "uri": "https://upload.wikimedia.org/wikipedia/commons/3/3a/Cat03.jpg", "position": "first" } ], "promptText": "The cat turns toward the camera.", "ratio": "1280:720", "duration": 5 }; const response = await fetch( "https://api.cometapi.com/runwayml/v1/image_to_video", { method: "POST", headers: { Authorization: `Bearer ${process.env.COMETAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify(payload), }, ); if (!response.ok) throw new Error(await response.text()); console.log((await response.json()).id); components: securitySchemes: bearerAuth: type: http scheme: bearer description: Use your CometAPI API key. ````