---
title: "Create Seedream images"
method: POST
path: "/v1/images/generations"
---

# Create Seedream images

`POST /v1/images/generations`

## Request body

- object — Parameters for Seedream image generation. Send JSON for text-to-image, image-to-image, and sequential prompt requests.
  - `model` string, required — Seedream model ID to use. Query `/v1/models` or open the [Models page](/overview/models) for available model IDs.
  - `prompt` string, required — Text prompt describing the image or edit goal. Use a concrete visual request, such as `a blue ceramic mug on a white table, soft studio lighting`.
  - `response_format` 'url' | 'b64_json' — Response image format. Use `url` for a temporary signed image URL, or `b64_json` when you need base64 image data in the response.
  - `size` string — Output resolution. Use a model-supported tier such as `2K` or a model-supported `WIDTHxHEIGHT` value such as `2048x2048`. Not every model ID accepts every tier.
  - `image` string[] — Optional reference images for image-to-image generation. Each item can be a public HTTPS URL or a data URI such as `data:image/png;base64,YOUR_BASE64_IMAGE`. Use an array even for one image. Reference images plus generated images must not exceed the provider limit.
  - `watermark` boolean — When `true`, requests a visible AI-generated watermark on the output image. Set `false` when your workflow handles disclosure separately.
  - `async` boolean — CometAPI asynchronous task mode. Set this to `true` to return immediately with `data.task_id`, then poll the Seedream image task endpoint `GET /v1/images/generations/{task_id}` for the final image data.
  - `output_format` 'png' | 'jpeg' — Output image file format. Use `png` when you need lossless output, or `jpeg` for smaller files.
  - `guidance_scale` number — Optional prompt-adherence control for model versions that support it. Higher values can follow the prompt more closely but may reduce naturalness. Omit this field when you do not need model-specific tuning.
  - `seed` integer — Optional random seed for reproducible attempts on model versions that support seeding. Use `-1` or omit the field for a random seed.
  - `sequential_image_generation` 'auto' | 'disabled' — Controls sequential prompt handling. Use `auto` to let the model return a sequence when the prompt calls for one. Use `disabled` for ordinary single-image requests.
  - `sequential_image_generation_options` object — Options for sequential prompt handling. This object is only used when `sequential_image_generation` is `auto`.
    - `max_images` integer — Maximum number of generated images allowed for the request. This is an upper bound, not a guarantee that the model returns that many images.

## Response `200`

Image generation response. Synchronous requests return completed image data. Async requests return a task response with `data.task_id`.

- union
  - object
    - `created` integer, required — Unix timestamp in seconds when the image response was created.
    - `data` object[], required — Generated image results. The array can contain one or more images depending on the request and model response.
      - `url` string — Temporary signed URL for the generated image. Save or download the image before the URL expires.
      - `b64_json` string — Base64-encoded image data when `response_format` is `b64_json`.
      - `size` string — Pixel dimensions of the generated image when returned by the model, such as `2048x2048`.
    - `usage` object — Usage information for the request. Fields vary by model and route.
      - `input_images` integer — Number of reference images received by the route, when reported.
      - `generated_images` integer — Number of generated images, when reported.
      - `output_tokens` integer — Image output tokens charged for the generated image data, when reported.
      - `total_tokens` integer — Total tokens reported for the request.
  - object
    - `code` string, required — Request status code. A successful async submit returns `success`.
    - `message` string — Optional status message.
    - `data` object, required
      - `task_id` string, required — Task ID to pass to `GET /v1/images/generations/{task_id}`.
      - `status` 'pending' | 'success' | 'failure', required — Task state for the submitted image generation job.
      - `data` object[], required — Empty at submit time. Poll the task endpoint to receive final image data.

---

[API](https://skmtc.net/cometapi/apis/create-api-key.md) · [All operations](https://skmtc.net/cometapi/apis/create-api-key/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/cometapi/create-api-key/versions/0863102dbf34/schema)