> ## Documentation Index > Fetch the complete documentation index at: https://docs.jiekou.ai/llms.txt > Use this file to discover all available pages before exploring further. # Seedream Parameters and usage are aligned with the official implementation; for detailed parameters, please refer directly to the official documentation. ## 1. Overview The Seedream image generation API uses the OpenAI-style image generation request format and supports text-to-image, image-to-image, and image editing. All four models share the same endpoint; the client only needs to select a model via the `model` field in the request body. ### Supported Models | Client Model ID | Model | Output Mode | | ------------------------------ | ----------------- | ----------------------------------- | | `seedream-4-0-250828` | Seedream 4.0 | Single image or multi-image group | | `seedream-4-5-251128` | Seedream 4.5 | Single image or multi-image group | | `seedream-5-0-260128` | Seedream 5.0 Lite | Single image or multi-image group | | `dola-seedream-5-0-pro-260628` | Seedream 5.0 Pro | Single image or layer decomposition | ## 2. Endpoint and Authentication ```http theme={null} POST https://{api_domain}/v3/bytedance/api/v3/images/generations ``` Request headers: ```http theme={null} Authorization: Bearer Content-Type: application/json ``` `{api_domain}` is the API domain of your platform. Requests must use POST, and the body must be JSON. ## 3. Request Parameters ### 3.1 Common Parameters Use a model ID from the table above. Image description. Supports both Chinese and English. Reference image URL or Base64 Data URL. You can pass a single image or an array. The exact number and image limits are subject to the restrictions of the selected model. Use a resolution tier supported by the model or an explicit `widthxheight`. If omitted, the model default is used. `url` or `b64_json`; defaults to `url`. Only supported by Seedream 5.0 Lite and 5.0 Pro: `jpeg` or `png`. Seedream 4.0 and 4.5 always output JPEG; passing `output_format` will be rejected. Whether to add an AI-generated watermark. The image endpoint does not support streaming output; do not pass `true`. ### 3.2 Model-Specific Parameters | Parameter | Applicable Models | Description | | ------------------------------------- | ------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | `sequential_image_generation` | 4.0, 4.5, 5.0 Lite | Toggle for multi-image group generation. When generating a group of images, fill it in according to the upstream protocol of the corresponding model; omit it when not using group generation. | | `sequential_image_generation_options` | 4.0, 4.5, 5.0 Lite | Options for multi-image group generation, used together with `sequential_image_generation`. | | 1K, 1.5K, and 2K tiers of `size` | 5.0 Pro | Pro supports these tiers as well as explicit `widthxheight`. Pro does not support group generation parameters. In the layer decomposition scenario, only tiers are supported (including auto) and it is enabled via `layer_decomposition: true` (see Model Limitations for details). | Seedream 5.0 Pro does not support `sequential_image_generation` or `sequential_image_generation_options`; passing either field will be rejected. Do not send other models' specific parameters to Pro. ### 3.3 Text-to-Image Example The following request uses Seedream 5.0 Pro as an example. All four models share the same endpoint; when using Seedream 4.0 or 4.5, `output_format` must be removed, and this field can only be included when using Seedream 5.0 Lite/Pro: ```bash theme={null} curl -sS -X POST "https://{api_domain}/v3/bytedance/api/v3/images/generations" \ -H "Authorization: Bearer " \ -H "Content-Type: application/json" \ -d '{ "model": "dola-seedream-5-0-pro-260628", "prompt": "一只戴着红色围巾的金毛犬，在雪山湖边的自然光下，电影感摄影", "size": "2K", "response_format": "url", "output_format": "jpeg", "watermark": true }' ``` ### 3.4 Image-to-Image Example `image` can be a single URL, a single Base64 Data URL, or an array of strings: ```json theme={null} { "model": "seedream-4-5-251128", "prompt": "将参考图中的人物和服装放在统一的城市夜景中，保持人物特征一致", "image": [ "https://example.com/person.png", "https://example.com/outfit.png" ], "size": "2560x1440", "response_format": "url" } ``` ### 3.5 Multi-Image Group Example (4.0, 4.5, and 5.0 Lite only) The group generation parameters apply to the first three models. Example: ```json theme={null} { "model": "seedream-5-0-260128", "prompt": "生成三张风格统一的四季海报", "sequential_image_generation": "auto", "sequential_image_generation_options": { "max_images": 3 }, "response_format": "url" } ``` Refer to the upstream protocol of the selected model to confirm the available values and count limits for the group generation parameters. ## 4. Response Example of a successful response: ```json theme={null} { "created": 1786000000, "model": "seedream-4-5-251128", "data": [ { "url": "https://example.com/generated-image.jpeg", "size": "2560x1440", "output_format": "jpeg" } ], "usage": { "generated_images": 1, "input_images": 0 } } ``` * When `response_format=url`, `data[].url` is returned; when `response_format=b64_json`, `data[].b64_json` is returned. * Seedream 4.0, 4.5, and 5.0 Lite can return multiple `data` items in multi-image group mode. * Seedream 5.0 Pro returns a single `data` item in the image generation scenario; when layer decomposition is enabled, it returns multiple `data` items (one base image + multiple layers), each additionally containing the layer stacking order `z_index` (0 for the base image), the name `name`, the description `description`, and the bounding box `bounding_box` (with absolute / normalized coordinates; the base image does not return this field). * `model` returns the client model ID used for this request. * The validity period of image URLs is determined by the platform and upstream services; download and save the images promptly after receiving the response. ## 5. Model Limitations ### Seedream 4.0 / 4.5 / 5.0 Lite * Supports text-to-image, image-to-image, and multi-image group generation. * Multi-image groups use `sequential_image_generation` and its options field. * For the number of input images, image size, resolution, and aspect ratio, refer to the upstream documentation of the corresponding model. Seedream 4.0 and 4.5 always output JPEG and do not support the request parameter `output_format`; Seedream 5.0 Lite supports `jpeg` and `png`. ### Seedream 5.0 Pro * Supports text-to-image, image-to-image from a single image, and multi-image fusion. * In the image generation scenario, it returns one successful image. When layer decomposition (`layer_decomposition: true`) is enabled, it returns one base image and multiple layers (up to 16 layers), in which case `data` contains multiple items. Multi-image group generation (`sequential_image_generation`) is not supported. * Does not support `sequential_image_generation` or `sequential_image_generation_options`. * `size` can be 1K, 1.5K, 2K, or an explicit `widthxheight`. * When explicit width and height are given, the aspect ratio and total pixel count must satisfy the model limitations; the actual dimensions of the output image are determined by `data[].size` in the response. * Supports layer decomposition: when `layer_decomposition: true` is set, a single input image is decomposed into one base image and up to 16 independently editable layers (each layer is a PNG with an alpha channel). In this scenario, `image` is required and only one image can be passed; passing multiple images results in an error. Layer decomposition is all-or-nothing: if any layer fails, the entire request fails; partial success is not supported. * `size` rules for layer decomposition: the base image resolution equals `size`; each layer's resolution is close to `size`, but each layer maintains the aspect ratio of its corresponding region in the original image, so the actual pixel counts of the layers differ. This means output images from the same request may fall into different pixel-based pricing tiers. `size` can be 1K, 1.5K, 2K, or auto, and defaults to auto. ## 6. Billing and Usage * 4.0, 4.5, and 5.0 Lite are billed by the number of successfully generated images; for multi-image group generation, billing is based on the actual number of successful outputs. * 5.0 Pro is billed by successfully output images; with multi-image input, the first reference image is free and additional reference images are metered separately; different output sizes correspond to different pricing tiers. When layer decomposition is enabled, the base image and each layer each count as one successful output image, and each is billed separately according to the pricing tier its `data[].size` pixel count falls into (for example, the base image may be in a high-pixel tier while some layers are in lower-pixel tiers); the final bill is the sum of the quantities across all tiers. * The usage unit is image or item. * For exact pricing, refer to the product pricing page of your platform. ## 7. Troubleshooting | Scenario | Recommendation | | ------------------------------------- | --------------------------------------------------------------------------------------------- | | Model not supported | Check that `model` exactly matches an entry in the table above. | | Missing prompt | The body must contain a non-empty prompt. | | Image cannot be read | Check the URL's accessibility, format, size, and pixel limits. | | `stream=true` | The image endpoint does not support streaming output; remove this field or set it to `false`. | | Group generation fields passed to Pro | Remove both `sequential_image_generation*` fields. | | Invalid size | Use a tier supported by the selected model or a `widthxheight` that meets the limitations. |