curl --request POST \
--url https://api.modellix.ai/api/v1/bytedance/seedream-5.0-pro-edit \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"prompt": "Convert this image to a watercolor painting style",
"image": "https://example.com/input.jpg"
}
'{
"code": 0,
"message": "success",
"data": {
"status": "pending",
"task_id": "task-abc123",
"model_id": "model-123",
"get_result": {
"method": "GET",
"url": "https://api.modellix.ai/api/v1/tasks/task-abc123"
}
}
}Seedream 5.0 Pro Edit
[Core Function] Seedream 5.0 Pro Edit is a professional-grade single-image editing (I2I) model. [Strengths] It supports interactive precise editing: edit locations can be specified via coordinates, selection boxes, or arrows described in the prompt, with strong element-level control and subject consistency. [Best For] Highly recommended for: precise local retouching, adding/removing/replacing objects at exact positions, style transfer of a single photo, and professional post-editing workflows. [Limitations] Do NOT use this model for text-to-image generation (an input image is required) or for blending multiple reference images; it accepts exactly one input image and outputs exactly one image (no batch or streaming). [Routing] For 2-10 reference images use Seedream 5.0 Pro Multi-Reference; for pure text-to-image use Seedream 5.0 Pro; choose Seedream 5.0 Lite Edit when batch outputs or more than 10 input images are required.
curl --request POST \
--url https://api.modellix.ai/api/v1/bytedance/seedream-5.0-pro-edit \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"prompt": "Convert this image to a watercolor painting style",
"image": "https://example.com/input.jpg"
}
'{
"code": 0,
"message": "success",
"data": {
"status": "pending",
"task_id": "task-abc123",
"model_id": "model-123",
"get_result": {
"method": "GET",
"url": "https://api.modellix.ai/api/v1/tasks/task-abc123"
}
}
}Authorizations
API Key authentication. Format: Bearer YOUR_API_KEY.
Body
Image editing instruction, supports Chinese and English. Maximum 10000 characters. We recommend keeping the prompt under 600 words. Interactive precise editing is supported: edit locations can be specified via coordinates, selection boxes, or arrows described in the prompt.
1 - 10000"Replace the object in the selection box (100,100)-(300,300) with a red vintage car"
Input image URL (or Base64 data URI). Single image only. Each image must be <= 30 MB, width and height > 14 px, aspect ratio within [1/16, 16], total pixels <= 36,000,000. Supported formats: JPEG, PNG, WEBP, BMP, TIFF, GIF, HEIC, HEIF.
"https://example.com/input.jpg"
Image size in format 'widthxheight'. Total pixels must be within [1280x720(921,600), 4,624,220] and aspect ratio within [1/16, 16], corresponding to the official 1K/2K resolution levels (3K/4K not supported). Recommended 2K sizes: 2048x2048 (1:1), 2816x1584 (16:9), 2368x1776 (4:3).
"2048x2048"
Prompt optimization mode. 'standard': higher quality with longer generation time. 'fast': faster generation with slightly lower quality.
standard, fast "standard"
Output image format. Supported values: 'jpeg' and 'png'.
jpeg, png "png"