Image Generationtextimage

Seedream 5.5

ByteDance Seed multimodal image generation model with precise multi-turn editing, pixel-level preservation of unedited regions, native RGBA transparent and semi-transparent output, more natural visual texture, and clearer small-text rendering.

Input

Generation mode

Describe the image with text only, no reference upload required.

Size
Watermark
Background
Output format
Layer decomposition
Ready to generateReady to generate

API Reference

POSThttps://api.token360.ai/v1/images/generations
curl https://api.token360.ai/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key" \
  -d '{
  "model": "seedream-5.5",
  "prompt": "A cute cat sitting on a windowsill",
  "size": "2k",
  "watermark": true,
  "background": "auto",
  "output_format": "png",
  "layer_decomposition": false
}'