> ## 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. # Generate Bria vector graphics > Use CometAPI POST /bria/text-to-vector to generate editable, scalable vector assets from text with Bria Base (Beta) for icons, logos, and illustrations. ## Overview Generate high-quality, editable vector graphic assets from text prompts. Ideal for creating scalable icons, logos, and illustrations using Bria's proprietary text-to-image foundation models. This interface is equivalent to `https://engine.prod.bria-api.com/v1/text-to-vector/base/3.2` For details, see the [Bria official documentation](https://docs.bria.ai/image-generation/v1-endpoints/text-to-vector-base). ## When to use it Use this endpoint when the final asset needs to remain editable or scalable, such as icons, simple illustrations, logos, and layout graphics. Use raster image generation instead when you need photorealistic detail or complex textures. ## First request Start with a short prompt that describes the object, style, and intended use. Keep the first request simple, then add brand, color, or composition constraints after you confirm the vector output is usable. ## Read the response The response returns vector output fields through the API playground. Persist the returned asset promptly if your workflow needs long-term storage or later editing. ## OpenAPI ````yaml api/openapi/image/bria/post-generate-vector-graphics-base.openapi.json POST /bria/text-to-vector openapi: 3.1.0 info: title: Generate Vector Graphics - Base (Beta) API version: 1.0.0 servers: - url: https://api.cometapi.com security: - bearerAuth: [] paths: /bria/text-to-vector: post: summary: Generate Vector Graphics - Base (Beta) operationId: generate_vector_graphics_base parameters: - name: Content-Type in: header required: false description: '' schema: type: string requestBody: required: true content: application/json: schema: type: object required: - prompt - guidance_method_2_scale properties: prompt: type: string description: >- The prompt you would like to use to generate images. Bria currently supports prompts in English only. default: A flat vector illustration of a sailboat at sunset num_results: type: integer description: >- The aspect ratio of the image. When a ControlNet is being used, the aspect ratio is defined by the guidance image and this parameter is ignored. Default `4` sync: type: boolean description: >- Determines the response mode. When true, responses are synchronous. With false, responses are asynchronous, immediately providing URLs for images that are generated in the background. Use polling for the URLs to retrieve images once ready. Default `false` aspect_ratio: type: string description: >- The aspect ratio of the image. Default `"1:1"` Enum `"1:1"` `"2:3"` `"3:2"` `"3:4"` `"4:3"` `"4:5"` `"5:4"` `"9:16"` `"16:9"` seed: type: integer description: >- You can choose whether you want your generated result to be random or predictable. You can recreate the same result in the future by using the seed value of a result from the response with the prompt, model type and model version. You can exclude this parameter if you are not interested in recreating your results. This parameter is optional. negative_prompt: type: string description: >- Specify here elements that you didn't ask in the prompt, but are being generated, and you would like to exclude. This parameter is optional. Bria currently supports prompts in English only. steps_num: type: integer description: >- The number of iterations the model goes through to refine the generated image. This parameter is optional. Default `30` text_guidance_scale: type: integer description: >- Determines how closely the generated image should adhere to the input text description. This parameter is optional. Default `5` prompt_content_moderation: type: boolean description: >- When enabled (default: true), the input prompt is scanned for NSFW or ethically restricted terms before image generation. If the prompt violates Bria's ethical guidelines, the request will be rejected with a 408 error. Default `true` content_moderation: type: boolean description: >- When enabled, applies content moderation to both input visuals and generated outputs. For input images: - Processing stops at the first image that fails moderation - Returns a 422 error with details about which parameter failed For synchronous requests (sync=true): - If all generated images fail moderation, returns a 422 error - If some images pass and others fail, returns a 200 response with successful generations and "blocked" objects for failed ones For asynchronous requests (sync=false): - Failed images are replaced with zero-byte files at their placeholder URLs - Successful images are stored at their original placeholder URLs Default `false` ip_signal: type: boolean description: >- Flags prompts with potential IP content. If detected, a warning will be included in the response. Default `false` guidance_method_1: type: string description: >- Which guidance type you would like to include in the generation. Up to 2 guidance methods can be combined during a single inference. This parameter is optional. Enum `"controlnet_canny"` `"controlnet_depth"` `"controlnet_recoloring"` `"controlnet_color_grid"` guidance_method_1_scale: type: integer description: |- The impact of the guidance. Default `1` guidance_method_1_image_file: type: string description: >- The image that should be used as guidance, in base64 format, with the method defined in guidance_method_1. Accepted formats are jpeg, jpg, png, webp. Maximum file size 12MB. If more then one guidance method is used, all guidance images must be of the same aspect ratio, and this will be the aspect ratio of the generated results. If guidance_method_1 is selected, an image must be provided. guidance_method_2: type: string description: >- Which guidance type you would like to include in the generation. Up to 2 guidance methods can be combined during a single inference. This parameter is optional. Enum `"controlnet_canny"` `"controlnet_depth"` `"controlnet_recoloring"` `"controlnet_color_grid"` guidance_method_2_scale: type: integer description: |- The impact of the guidance. Default `1` default: 1 guidance_method_2_image_file: type: string description: >- The image that should be used as guidance, in base64 format, with the method defined in guidance_method_2. Accepted formats are jpeg, jpg, png, webp. Maximum file size 12MB. If more then one guidance method is used, all guidance images must be of the same aspect ratio, and this will be the aspect ratio of the generated results. If guidance_method_1 is selected, an image must be provided. image_prompt_mode: type: string description: >- - `regular`: Uses the image’s content, style elements, and color palette to guide generation. - `style_only`: Uses the image’s high-level style elements and color palette to influence the generated output. The support for image prompt is currently available only when model_version="2.3". Default `"regular"` Enum `"regular"` `"style_only"` image_prompt_file: type: string description: >- The image file to be used as guidance, in base64 format. Accepted formats are jpeg, jpg, png, webp. The support for image prompt is currently available only when model_version="2.3". Maximum file size 12MB. This image can be of any aspect ratio, even when it's not alligned with the one defined in the parameter 'aspect_ratio' or by visuals provided to the ControlNets. image_prompt_urls: type: array description: >- A list of URLs of images that should be used as guidance. The images can be of different aspect ratios. Accepted formats are jpeg, jpg, png, webp. The URLs should point to accessible, publicly available images. The support for image prompt is currently available only when model_version="2.3". items: type: string description: url image_prompt_scale: type: integer description: >- The impact of the provided image on the generated results. A value between 0.0 (no impact) and 1.0 (full impact). Default `1` default: prompt: A flat vector illustration of a sailboat at sunset guidance_method_2_scale: 1 examples: Example 1: summary: Example 1 value: prompt: a book num_results: 2 sync: false responses: '200': description: Success content: application/json: schema: type: object properties: {} x-codeSamples: - lang: Shell label: Default source: | curl https://api.cometapi.com/bria/text-to-vector \ -H "Authorization: Bearer $COMETAPI_KEY" \ -H "Content-Type: application/json" \ -d '{ "prompt": "a book", "num_results": 2, "sync": false }' - lang: Python label: Default source: > import os import requests response = requests.post( "https://api.cometapi.com/bria/text-to-vector", headers={"Authorization": "Bearer " + os.environ["COMETAPI_KEY"]}, json={ "prompt": "a book", "num_results": 2, "sync": False }, ) print(response.json()) # the route responds synchronously with result[].urls - lang: JavaScript label: Default source: > const response = await fetch("https://api.cometapi.com/bria/text-to-vector", { method: "POST", headers: { Authorization: `Bearer ${process.env.COMETAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "prompt": "a book", "num_results": 2, "sync": false }), }); console.log(await response.json()); // the route responds synchronously with result[].urls components: securitySchemes: bearerAuth: type: http scheme: bearer description: Bearer token authentication. Use your CometAPI key. ````