> ## Documentation Index
> Fetch the complete documentation index at: https://docs.anyfast.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# seedream-5.0-lite
> Seedream 5.0 Lite text-to-image and image-to-image API.
Use `seedream-5-0-lite-260128` with the same synchronous endpoint for single images, image editing, and sequential image generation.
Select the **Special-Ns** resource group for specific content requests.
## Create an image
`POST /v1/images/generations`
```bash cURL theme={null}
curl --request POST \
--url https://www.anyfast.ai/v1/images/generations \
--header 'Authorization: Bearer ' \
--header 'Content-Type: application/json' \
--data '{
"model": "seedream-5-0-lite-260128",
"prompt": "Create four coherent storyboard frames showing an astronaut repairing a spacecraft",
"size": "2K",
"seed": 42,
"sequential_image_generation": "auto",
"sequential_image_generation_options": { "max_images": 4 },
"response_format": "url",
"output_format": "png",
"watermark": false,
"optimize_prompt_options": { "mode": "standard" }
}'
```
Must be `seedream-5-0-lite-260128`.
The image-generation prompt.
`2K`, `3K`, `4K`, or a supported explicit pixel size.
Random seed.
Use `auto` for sequential images or `disabled` for a single image.
Maximum number of sequential images.
`url` or `b64_json`. URLs expire after 24 hours.
`png` or `jpeg`.
Whether to add an AI-generated watermark.
Prompt optimization mode.
## Create an image
`POST /v1/images/generations`
```bash cURL theme={null}
curl --request POST \
--url https://www.anyfast.ai/v1/images/generations \
--header 'Authorization: Bearer ' \
--header 'Content-Type: application/json' \
--data '{
"model": "seedream-5-0-lite-260128",
"prompt": "Replace the outfit in image one with the outfit in image two while preserving identity and pose",
"image": [
"https://example.com/person.png",
"https://example.com/outfit.png"
],
"size": "2K",
"response_format": "url",
"output_format": "png",
"watermark": false
}'
```
Must be `seedream-5-0-lite-260128`.
The image-editing instruction.
An image URL, Base64 data URI, or up to 14 reference images.
`2K`, `3K`, `4K`, or a supported explicit pixel size.
Random seed.
Use `auto` for sequential images or `disabled` for a single image.
Maximum output count. Reference and generated images together must not exceed 15.
`url` or `b64_json`. URLs expire after 24 hours.
`png` or `jpeg`.
Whether to add an AI-generated watermark.
Prompt optimization mode.
Supported formats are jpeg, png, webp, bmp, tiff, gif, heic, and heif. Each image must be at most 30 MB, have an aspect ratio in `[1/16, 16]`, have both dimensions greater than 14 px, and contain no more than 36,000,000 pixels.
## Headers
Bearer authentication in the form `Bearer `.
Request body format.
## Response
```json 200 theme={null}
{
"model": "seedream-5-0-lite-260128",
"created": 1775029815,
"data": [{
"url": "https://example.com/generated-image.png",
"size": "2048x2048"
}],
"usage": {
"generated_images": 1,
"output_tokens": 16384,
"total_tokens": 16384
}
}
```
The model ID used for the request.
Creation time as a Unix timestamp in seconds.
Generated images.
Temporary image URL when `response_format` is `url`.
Base64 image data when `response_format` is `b64_json`.
Generated image dimensions.
Number of generated images.
Output token count.
Total token count.
## Error responses
Error responses use an `error` object with `code`, `message`, and `type` fields.
Error information.
Machine-readable error code.
Human-readable error message.
Error category.
Invalid request or unsupported parameter value.
```json theme={null}
{ "error": { "code": "invalid_request_error", "message": "Invalid request parameter", "type": "invalid_request_error" } }
```
Missing or invalid API key.
```json theme={null}
{ "error": { "code": "unauthorized", "message": "Invalid API key", "type": "authentication_error" } }
```
Rate limit exceeded.
```json theme={null}
{ "error": { "code": "rate_limit_exceeded", "message": "Rate limit exceeded", "type": "rate_limit_error" } }
```