API docs / Image models

Seedream 4.5 API

Generates high-quality images from text prompts with superior cinematic aesthetics and strong spatial understanding. Features refined lighting, shading, and rendering for polished, film-like visuals. Supports both text-to-image and image-to-image generation with single or multi-reference inputs. Offers precise instruction following for complex prompts and maintains stable subjects across multiple images. Includes sequential image generation mode that can automatically create multiple related images like story scenes or character variations. Supports 2K and 4K resolution output with various aspect ratios. Optimized for professional workflows in e-commerce, film, advertising, gaming, education, and architectural design.

Model id
bytedance/seedream-4.5
Provider
Bytedance
Output
Image
Price
From 14 credits per run, the same as on voor.ai. Options such as length or resolution can change it.

Request

POST https://voor.ai/v1/generations with "model": "bytedance/seedream-4.5". Poll GET /v1/tasks/{id} or receive the signed webhook. See the overview for keys, idempotency, webhooks and errors.

curl https://voor.ai/v1/generations \
  -H "Authorization: Bearer $VOOR_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
  "model": "bytedance/seedream-4.5",
  "input": {
    "prompt": "A red fox standing in fresh snow at golden hour, soft light"
  },
  "callback_url": "https://example.com/webhooks/voor"
}'

# Then poll the task (or wait for the webhook):
curl https://voor.ai/v1/tasks/TASK_ID \
  -H "Authorization: Bearer $VOOR_API_KEY"

Input parameters

NameTypeDetails
promptrequiredstring

Text prompt for image generation

reference_imagesarray of URLs

Input image(s) for image-to-image generation. List of 1-14 images for single or multi-reference generation.

Default: []

Up to 10 files · Accepts image/*

aspect_ratiostring

Default: match_input_image

One of: match_input_image, 1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3, 21:9

resolutionstring

Default: 2k

One of: 2k, 4k

max_imagesnumber

Maximum number of images to generate when sequential_image_generation='auto'. Range: 1-15. Total images (input + generated) cannot exceed 15.

Default: 1

Min 1 · Max 15

sequential_image_generationstring

Default: disabled

One of: disabled, auto