Bytedance Uso API Documentation

Bytedance Uso API Documentation

Playground

Try it on WaveSpeedAI!

USO (Unified Style-Subject Optimized) by unifies style-driven and subject-driven generation to produce consistent outputs that blend artistic style with subject fidelity. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

USO combines subject and style references to generate images that follow your prompt while preserving visual qualities from the supplied references.


Why Choose This?

  • Subject and style guidance
    Use reference images to guide the subject, identity, appearance, or visual style of the generated image.

  • Multi-reference input
    Provide up to four reference images in a single request.

  • Prompt-guided generation
    Add a prompt to describe the desired image, or leave it empty for reference-driven generation.

  • Reproducible results
    Set a seed to make generations easier to reproduce.


Parameters

ParameterRequiredDescription
reference_imagesYesOne to four reference images. The first image is used as the content reference; following images provide style or additional visual references.
promptNoText instructions for the generated image. May be left empty for reference-driven generation.
seedNoRandom seed for reproducible generation. Use -1 for a random seed.
sync_modelNoSync the model to the latest version. Default: false.

How to Use

  1. Add one to four images to reference_images.
  2. Put the main content reference first, followed by any style or additional references.
  3. Add a prompt to describe the desired result, or leave it empty for reference-driven generation.
  4. Set a seed for reproducible results, or use -1 for a random seed.
  5. Submit the request and retrieve the generated image URL from the result.

Pricing

Pricing is $0.50 per generated image, based on an output limit of up to 4 MP.

Output sizePrice
Up to 4 MP$0.50

Best Use Cases

  • Consistent subject generation — Guide the result with one or more subject references.
  • Style transfer — Apply a visual style from reference images to a new composition.
  • Creative exploration — Combine visual references with a prompt to explore different directions.
  • Marketing and concept art — Create images that follow a consistent subject or visual identity.

Pro Tips

  • Put the most important content or subject image first.
  • Use clear reference images with minimal compression artifacts.
  • Add a concise prompt when you need to specify how the references should be combined.
  • Use a fixed seed when comparing prompt changes.

Notes

  • Provide between one and four reference images.
  • The output-size limit for this pricing is 4 MP.
  • seed and sync_model do not add separate charges.

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'
{
  "reference_images": [
    "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
  ]
}
JSON
)

# 1. Submit the prediction once. Never retry this request automatically:
# a retry after an unclear failure can create a second, billed task.
CHECK='The task may already exist. Check History or the predictions list before submitting again.'
if ! SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --connect-timeout 10 --max-time 60 \
  -X POST "https://api.wavespeed.ai/api/v3/bytedance/uso" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}"); then
  printf 'Submit failed. %s\n' "${CHECK}" >&2
  exit 1
fi

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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id. %s\n' "${CHECK}" >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction reaches a final status.
BODY_FILE=$(mktemp)
trap 'rm -f "${BODY_FILE}"' EXIT
while true; do
  # Transient errors (429, 5xx) are retried, honoring Retry-After.
  HTTP_CODE=$(curl --silent --show-error --fail-with-body \
    --connect-timeout 10 --max-time 60 --retry 5 --retry-delay 2 \
    --output "${BODY_FILE}" --write-out '%{http_code}' \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}" || true)
  case "${HTTP_CODE}" in
    2??) ;;
    000|429|5??)  # dropped connection or temporary error: keep polling
      printf 'Task %s: HTTP %s, polling again in 10s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      sleep 10; continue ;;
    *) printf 'Task %s: HTTP %s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      cat "${BODY_FILE}" >&2; exit 1 ;;
  esac
  RESULT=$(jq 'if type == "object" and has("data") then .data else . end' "${BODY_FILE}")
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted)
      printf 'Task %s ended with status %s\n' "${PREDICTION_ID}" "${STATUS}" >&2
      printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Retry temporary errors only while polling, never the submit request. Errors, retries and timeouts

Parameters

Task Submission Parameters

Request Parameters

ParameterTypeRequiredDefaultRangeDescription
reference_imagesarray<string>Yes-0 ~ 4 itemsA list of images to use as style references. At least 1 image is required. max 4 images.
promptstringNo-The positive prompt for the generation.
seedintegerNo--The random seed to use for the generation. -1 means a random seed will be used.

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayOutput values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.statusstringTask status. completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses.
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Request Parameters

ParameterTypeRequiredDefaultDescription
idstringYes-Task ID

Result Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
dataobjectThe prediction data object containing all details
data.idstringUnique identifier for the prediction
data.modelstringModel ID used for the prediction
data.outputsarray<string | object>Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model.
data.urlsobjectObject containing related API endpoints
data.statusstringStatus: completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses
data.created_atstringISO timestamp of when the request was created
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
© 2026 WaveSpeedAI. All rights reserved.