> ## 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 et Runway-bilde > Generer bilder med Gen-4 Image eller Gen-4 Image Turbo ved hjelp av tekst og referansebilder. Bruk dette endepunktet til å generere et bilde fra en Prompt, med valgfrie referanse bilder for `gen4_image`. Send CometAPI API-nøkkelen din med Bearer-autentisering og en JSON-forespørselstekst. ## Velg en modell og referanser Hver forespørsel krever `model`, `promptText` og `ratio`. | Modell | `referenceImages` | | ------------------ | ------------------------------------------------------------------------------------------------------ | | `gen4_image` | Valgfritt. Utelat feltet eller bruk `[]` for generering med bare tekst, eller oppgi opptil tre bilder. | | `gen4_image_turbo` | Oppgi ett til tre bilder. | For `gen4_image_turbo` er `referenceImages` obligatorisk og må inneholde ett til tre bilder. Hvert referanseobjekt inneholder en bilde-`uri` og en valgfri `tag`. Bruk en tagg på 3 til 16 små bokstaver, sifre eller understreker, og den må starte med en bokstav. Referer til den i `promptText` som `@tag`, for eksempel `@cat_ref`. Bilde-URI-er godtar tilgjengelige HTTPS-URL-er eller Base64-data-URI-er for bilder på opptil 5 MB. Prompt godtar 1 til 1 000 UTF-16-kodeenheter. ## Velg dimensjoner Angi `ratio` til ett av de nøyaktige dimensjonsparene i skjemaet. For eksempel `1024:1024` ber `1280:720` om et kvadratisk bilde, et liggende bilde, og `720:1280` et stående bilde. Bruk `ratio` for å velge dimensjoner; ikke send `resolution` eller `size` med disse modellene. For en eksplisitt seed for sampling bruker du `1` til `4294967295`. Utelatelse eller `0` velger en tilfeldig seed. Hvis du inkluderer `contentModeration`, angir du dens `publicFigureThreshold` til `auto` eller `low`; ellers utelater du objektet. ## Hent resultatet Lagre den returnerte `id` og bruk [Hent en Runway-oppgave](./runway-to-get-task-details). Når `status` er `SUCCEEDED`, leser du de genererte bilde-URL-ene i `output`. ## OpenAPI ````yaml api/openapi/video/runway/official-format/post-generate-an-image-from-text.openapi.json POST /runwayml/v1/text_to_image openapi: 3.1.0 info: title: Create a Runway image version: 1.0.0 description: Create a Runway image through CometAPI. servers: - url: https://api.cometapi.com security: - bearerAuth: [] paths: /runwayml/v1/text_to_image: post: summary: Create a Runway image description: >- Submit a JSON request and save the returned id. Use GET /runwayml/v1/tasks/{id} to retrieve the result. operationId: generate_an_image_from_text requestBody: required: true content: application/json: schema: oneOf: - title: gen4_image type: object properties: model: type: string description: Model ID for this request variant. const: gen4_image enum: - gen4_image promptText: description: >- Describe the requested scene or motion in 1 to 1,000 UTF-16 code units. type: string minLength: 1 maxLength: 1000 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: - '1024:1024' - '1080:1080' - '1168:880' - '1360:768' - '1440:1080' - '1080:1440' - '1808:768' - '1920:1080' - '1080:1920' - '2112:912' - '1280:720' - '720:1280' - '720:720' - '960:720' - '720:960' - '1680:720' referenceImages: description: >- Optional array of up to three reference images. Omit it or use an empty array for text-only generation. maxItems: 3 type: array 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 tag: type: string description: >- Optional lowercase reference label. Refer to it as @tag in promptText. minLength: 3 maxLength: 16 pattern: ^[a-z][a-z0-9_]+$ required: - uri additionalProperties: false minItems: 0 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 required: - promptText - ratio - model additionalProperties: false description: Request parameters for gen4_image. - title: gen4_image_turbo type: object properties: model: type: string description: Model ID for this request variant. const: gen4_image_turbo enum: - gen4_image_turbo promptText: description: >- Describe the requested scene or motion in 1 to 1,000 UTF-16 code units. type: string minLength: 1 maxLength: 1000 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: - '1024:1024' - '1080:1080' - '1168:880' - '1360:768' - '1440:1080' - '1080:1440' - '1808:768' - '1920:1080' - '1080:1920' - '2112:912' - '1280:720' - '720:1280' - '720:720' - '960:720' - '720:960' - '1680:720' referenceImages: description: >- One to three reference images. An empty array, null, or an omitted field is not a valid request for this model. minItems: 1 maxItems: 3 type: array 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 tag: type: string description: >- Optional lowercase reference label. Refer to it as @tag in promptText. minLength: 3 maxLength: 16 pattern: ^[a-z][a-z0-9_]+$ required: - uri additionalProperties: false 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 required: - promptText - ratio - referenceImages - model additionalProperties: false description: Request parameters for gen4_image_turbo. discriminator: propertyName: model examples: Gen-4 Image with a reference: summary: Gen-4 Image with a reference value: model: gen4_image promptText: A watercolor portrait of @cat_ref. ratio: '1024:1024' referenceImages: - uri: >- https://upload.wikimedia.org/wikipedia/commons/3/3a/Cat03.jpg tag: cat_ref Gen-4 Image from text: summary: Gen-4 Image from text value: model: gen4_image promptText: A paper boat on calm water at sunrise. ratio: '1024:1024' Gen-4 Image Turbo: summary: Gen-4 Image Turbo value: model: gen4_image_turbo promptText: A watercolor portrait of @cat_ref. ratio: '1024:1024' referenceImages: - uri: >- https://upload.wikimedia.org/wikipedia/commons/3/3a/Cat03.jpg tag: cat_ref 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 Image with a reference source: | curl "https://api.cometapi.com/runwayml/v1/text_to_image" \ --request POST \ --header "Authorization: Bearer $COMETAPI_KEY" \ --header "Content-Type: application/json" \ --data '{ "model": "gen4_image", "promptText": "A watercolor portrait of @cat_ref.", "ratio": "1024:1024", "referenceImages": [ { "uri": "https://upload.wikimedia.org/wikipedia/commons/3/3a/Cat03.jpg", "tag": "cat_ref" } ] }' - lang: Python label: Gen-4 Image with a reference source: | import os import requests payload = {'model': 'gen4_image', 'promptText': 'A watercolor portrait of @cat_ref.', 'ratio': '1024:1024', 'referenceImages': [{'uri': 'https://upload.wikimedia.org/wikipedia/commons/3/3a/Cat03.jpg', 'tag': 'cat_ref'}]} response = requests.post( "https://api.cometapi.com/runwayml/v1/text_to_image", headers={"Authorization": "Bearer " + os.environ["COMETAPI_KEY"]}, json=payload, timeout=60, ) response.raise_for_status() print(response.json()["id"]) - lang: JavaScript label: Gen-4 Image with a reference source: | const payload = { "model": "gen4_image", "promptText": "A watercolor portrait of @cat_ref.", "ratio": "1024:1024", "referenceImages": [ { "uri": "https://upload.wikimedia.org/wikipedia/commons/3/3a/Cat03.jpg", "tag": "cat_ref" } ] }; const response = await fetch( "https://api.cometapi.com/runwayml/v1/text_to_image", { 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 Image from text source: | curl "https://api.cometapi.com/runwayml/v1/text_to_image" \ --request POST \ --header "Authorization: Bearer $COMETAPI_KEY" \ --header "Content-Type: application/json" \ --data '{ "model": "gen4_image", "promptText": "A paper boat on calm water at sunrise.", "ratio": "1024:1024" }' - lang: Python label: Gen-4 Image from text source: | import os import requests payload = {'model': 'gen4_image', 'promptText': 'A paper boat on calm water at sunrise.', 'ratio': '1024:1024'} response = requests.post( "https://api.cometapi.com/runwayml/v1/text_to_image", headers={"Authorization": "Bearer " + os.environ["COMETAPI_KEY"]}, json=payload, timeout=60, ) response.raise_for_status() print(response.json()["id"]) - lang: JavaScript label: Gen-4 Image from text source: | const payload = { "model": "gen4_image", "promptText": "A paper boat on calm water at sunrise.", "ratio": "1024:1024" }; const response = await fetch( "https://api.cometapi.com/runwayml/v1/text_to_image", { 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 Image Turbo source: | curl "https://api.cometapi.com/runwayml/v1/text_to_image" \ --request POST \ --header "Authorization: Bearer $COMETAPI_KEY" \ --header "Content-Type: application/json" \ --data '{ "model": "gen4_image_turbo", "promptText": "A watercolor portrait of @cat_ref.", "ratio": "1024:1024", "referenceImages": [ { "uri": "https://upload.wikimedia.org/wikipedia/commons/3/3a/Cat03.jpg", "tag": "cat_ref" } ] }' - lang: Python label: Gen-4 Image Turbo source: | import os import requests payload = {'model': 'gen4_image_turbo', 'promptText': 'A watercolor portrait of @cat_ref.', 'ratio': '1024:1024', 'referenceImages': [{'uri': 'https://upload.wikimedia.org/wikipedia/commons/3/3a/Cat03.jpg', 'tag': 'cat_ref'}]} response = requests.post( "https://api.cometapi.com/runwayml/v1/text_to_image", headers={"Authorization": "Bearer " + os.environ["COMETAPI_KEY"]}, json=payload, timeout=60, ) response.raise_for_status() print(response.json()["id"]) - lang: JavaScript label: Gen-4 Image Turbo source: | const payload = { "model": "gen4_image_turbo", "promptText": "A watercolor portrait of @cat_ref.", "ratio": "1024:1024", "referenceImages": [ { "uri": "https://upload.wikimedia.org/wikipedia/commons/3/3a/Cat03.jpg", "tag": "cat_ref" } ] }; const response = await fetch( "https://api.cometapi.com/runwayml/v1/text_to_image", { 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. ````