Bytedance Seedream V5.0 Lite Sequential API Documentation

Bytedance Seedream V5.0 Lite Sequential API Documentation

Playground

Seedream 5.0 Lite Sequential generates multi-image sets with consistent characters and objects, unifying palette, lighting, and style across all outputs. Supports up to 4K results for campaigns, storyboards, and product lines. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Seedream V5.0 Lite Sequential is multi-image text-to-image model designed to generate a series of coherent images from a single prompt. Describe multiple scenes in one prompt — the model generates a consistent visual sequence with stable character identity and style continuity, perfect for storytelling, storyboards, and visual narratives.

Why Choose This?

• Multi-image generation Generate multiple related images in a single run with consistent style and characters.

• Character consistency Maintains character identity, proportions, and visual style across the entire sequence.

• Narrative storytelling Create visual stories by describing multiple scenes in one prompt.

• High resolution support Custom width and height from 1440 to 8192 pixels.

• Flexible aspect ratios Multiple presets including 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, and 2:3.

• Prompt Enhancer Built-in tool to automatically improve your descriptions.

Parameters

How to Use

1. Set max_images first — specify how many images you want to generate.
2. Write your prompt — describe each image in sequence, starting with the count.
3. Choose size — select a preset or customize width/height.
4. Use Prompt Enhancer (optional) — click to automatically refine your description.
5. Run — submit and download your image sequence.

Important: Specify the number of images in your prompt to match max_images!

Example prompt format:

• max_images = 2
• Prompt: “2 images. First, a young princess in a torn royal dress sneaking through a dark castle corridor… Second, the princess and the cloaked figure riding together on horseback at dawn…”

Pricing

Billing Rules

• Base price: $0.035 per output image
• Total cost = $0.035 × max_images

Best Use Cases

• Visual Storytelling — Create sequential narratives with consistent characters.
• Storyboards — Generate scene-by-scene illustrations for projects.
• Comic & Manga — Produce multi-panel visual sequences.
• Character Series — Generate variations of the same character in different scenarios.
• Marketing Campaigns — Create cohesive visual series for brand storytelling.
• Social Media Content — Produce carousel posts with narrative continuity.

Pro Tips

• Always specify the number of images at the start of your prompt (e.g., “2 images. First… Second…”).
• Use “First,” “Second,” “Third,” etc. to clearly separate each image description.
• Include consistent character descriptions across scenes for better identity preservation.
• Keep style references consistent throughout the prompt (e.g., “fantasy art, cinematic” for all scenes).
• Start with fewer images (2–4) to test consistency before generating larger sequences.

Notes

• Prompt is the only required field.
• Always match max_images setting with the number specified in your prompt.
• Resolution range: 1440–8192 pixels for both width and height.
• Ensure your prompts comply with content guidelines.

Related Models

• Seedream V5.0 Lite Edit Sequential — Multi-image editing with consistent identity.
• Seedream V5.0 Lite Text-to-Image — Single image generation.
• Seedream V5.0 Lite Edit — Single-image editing with style transfer.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "size": "2048*2048",
  "max_images": 1,
  "output_format": "jpeg"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/bytedance/seedream-v5.0-lite/sequential" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters