> ## Documentation Index > Fetch the complete documentation index at: https://docs.haitoken.ai/llms.txt > Use this file to discover all available pages before exploring further. # Seedream image generation > Image generation compatible with the official Seedream protocol, supporting text-to-image, image-to-image, sequential images, and layer decomposition This endpoint is consistent with the official Seedream protocol. It extends the OpenAI Images protocol with Seedream-specific parameters, supporting reference image input, sequential image generation, and layer decomposition. ## Features * Compatible with the base parameters of the OpenAI Images protocol (`prompt`, `size`, `output_format`, and more) * Supports image-to-image generation by passing a reference image via `image` (URL or Base64) * Supports sequential image generation via `sequential_image_generation`, producing a set of related images from your input, with a configurable maximum count * Supports layer decomposition via `layer_decomposition`, returning decomposed layers with bounding box information * Supports prompt optimization via `optimize_prompt_options` (`standard` / `fast` modes) * Supports both resolution tiers such as `1K` and `2K` and explicit sizes such as `1024x1024` * Supports watermark control via `watermark` ## Authentication Include the `Authorization` header in the format `Bearer YOUR_API_KEY`. ## Supported image models Models in the seedream series. ## Quick example ```python Python theme={null} import requests url = "https://api.haitoken.ai/v1/images/generations" headers = { "Authorization": "Bearer YOUR_API_KEY", "Content-Type": "application/json" } data = { "model": "dola-seedream-5.0-pro", "prompt": "An orange cat wearing an astronaut helmet floating in space with Earth in the background", "size": "2K", "watermark": False, "response_format": "url" } response = requests.post(url, json=data, headers=headers) print(response.json()) ``` ```javascript Node.js theme={null} const response = await fetch('https://api.haitoken.ai/v1/images/generations', { method: 'POST', headers: { 'Authorization': 'Bearer YOUR_API_KEY', 'Content-Type': 'application/json' }, body: JSON.stringify({ model: 'dola-seedream-5.0-pro', prompt: 'An orange cat wearing an astronaut helmet floating in space with Earth in the background', size: '2K', watermark: false, response_format: 'url' }) }); const data = await response.json(); console.log(data); ``` ```curl cURL theme={null} curl -X POST 'https://api.haitoken.ai/v1/images/generations' \ -H 'Authorization: Bearer YOUR_API_KEY' \ -H 'Content-Type: application/json' \ -d '{ "model": "dola-seedream-5.0-pro", "prompt": "An orange cat wearing an astronaut helmet floating in space with Earth in the background", "size": "2K", "watermark": false, "response_format": "url" }' ``` A successful generation returns the image data: ```json theme={null} { "created": 1787875200, "model": "dola-seedream-5.0-pro", "data": [ { "url": "https://example.com/images/generated-1.png", "size": "2048x2048" } ], "usage": { "output_tokens": 8320, "total_tokens": 8320, "generated_images": 1, "input_images": 0 } } ``` ## Next steps * See [OpenAI image generation](/docs/en/api-reference/images/openai/generation) for the base protocol parameters * See [OpenAI image edit](/docs/en/api-reference/images/openai/edit) to edit existing images * See the [model list](/docs/en/api-reference/models/list-models) for available image models ## OpenAPI ````yaml en/api-reference/images/seedream/generation/openapi.json POST /v1/images/generations openapi: 3.0.1 info: title: Default Module description: '' version: 1.0.0 servers: [] security: [] tags: [] paths: /v1/images/generations: post: tags: [] summary: Seedream image generation parameters: - name: Authorization in: header description: API Key token (Bearer sk-xxx) required: true example: 'Bearer ' schema: type: string - name: Content-Type in: header description: '' example: application/json schema: type: string requestBody: content: application/json: schema: description: '' type: object properties: model: type: string description: Model name prompt: type: string description: Text prompt image: type: object properties: {} description: >- Reference image, URL or Base64 string (Seedream extension parameter, used for image-to-image) layer_decomposition: type: boolean description: >- Whether to decompose layers: true to decompose, false not to (default) size: type: string description: Image size, e.g. "1024x1024", "1K", "2K" optimize_prompt_options: $ref: '#/components/schemas/OptimizePromptOptions' description: Prompt optimization options output_format: type: string description: Output image format, e.g. "png", "jpeg", "webp" background: type: string description: >- Background of the generated image: "transparent" / "opaque" / "auto"; defaults to "auto" output_compression: type: integer description: Output compression level response_format: type: string description: Response format, "url" or "b64_json" sequential_image_generation: type: string description: >- Controls whether to disable sequential image generation (sequential images: a set of related images generated from your input). "auto"/"disabled"; defaults to "disabled" sequential_image_generation_options: $ref: '#/components/schemas/SequentialImageGenerationOptions' description: >- Sequential image generation configuration. Only effective when sequential_image_generation is auto. stream: type: boolean description: Whether to use streaming (SSE) responses watermark: type: boolean description: Whether to add a watermark required: - model - prompt examples: {} responses: '200': description: '' content: application/json: schema: type: object properties: created: type: integer description: Image generation timestamp (Unix seconds) format: int64 model: type: string description: Model used data: type: array items: description: >- Single image data. Contains the image URL or Base64 data, the revised prompt, the image size, and more. Compatible with the OpenAI DALL-E format (b64_json / revised_prompt) and common image model response formats. type: object properties: b64_json: type: string description: >- Base64-encoded image data (returned when response_format is b64_json) revised_prompt: type: string description: Prompt revised by the model (DALL-E 3 feature) output_format: type: string description: Output image format, e.g. "png", "jpeg", "webp" z_index: type: integer description: Layer stacking order name: type: string description: Layer name bounding_box: $ref: '#/components/schemas/BoundingBox' description: Layer bounding box url: type: string description: Publicly accessible image URL size: type: string description: Image size, e.g. "1024x1024" error: $ref: '#/components/schemas/ImageError' description: >- Error that occurred while generating this image (populated on partial success) description: type: string description: Layer description description: Generated image data list usage: description: Token and image usage statistics type: object properties: output_tokens: type: integer description: Output token consumption total_tokens: type: integer description: Total token consumption generated_images: type: integer description: Number of images generated in this request input_images: type: integer description: Number of input images in this request description: '' headers: {} deprecated: false security: [] components: schemas: OptimizePromptOptions: type: object properties: mode: type: string description: 'Optimization mode: standard/fast' SequentialImageGenerationOptions: type: object properties: max_images: type: integer description: Maximum number of images to generate BoundingBox: type: object properties: absolute: type: array items: type: integer description: Absolute coordinates normalized: type: array items: type: integer description: Normalized coordinates ImageError: type: object properties: code: type: string description: Error code message: type: string description: Error description type: type: string description: Error type classification param: type: string description: Request parameter that caused the error ````