prompt | string | yes | - | Text prompt. With image attached, becomes an editing instruction. For batch mode, describe each image sequentially. |
aspect_ratio | enum | no | "auto" | Auto lets the model pick; with a reference image it follows the closest preset. · Allowed: auto, 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9 |
quality | enum | no | "2K" | 2K ≈ 4MP. 3K ≈ 9MP. · Allowed: 2K, 3K |
use_custom_size | boolean | no | false | Override aspect_ratio + quality with explicit pixels. |
custom_width | number | no | - | Pixels. Total area must be in [2.56MP, 10.4MP]; aspect must be in [1:16, 16:1]. Only when use_custom_size=true. · Range: 1024 – 3072 |
custom_height | number | no | - | Pixels. Total area must be in [2.56MP, 10.4MP]; aspect must be in [1:16, 16:1]. Only when use_custom_size=true. · Range: 1024 – 3072 |
image | array | no | - | Up to 14 reference image URLs for editing. Triggers image-edit mode. |
batch_enabled | boolean | no | false | Generate a cohesive set of related images from a single prompt. |
max_images | number | no | 4 | Batch mode only. Maximum images in the set; the model decides actual count. You’re billed only for images returned. · Range: 1 – 15 |
watermark | boolean | no | false | Forwarded to BytePlus as watermark. When true, the upstream Seedream service stamps a small ByteDance/Seedream provenance mark on each generated image. EmpirioLabs does not add any watermark of its own. |
output_format | enum | no | "png" | Output media file format (mp3, wav, mp4, png, jpg, etc., depending on the endpoint). · Allowed: jpeg, png |
response_format | enum | no | "url" | url (default) returns a signed URL; b64_json returns inline base64. · Allowed: url, b64_json |
