Vidu Text To Video Q1

Vidu Text To Video Q1

Playground

Vidu Text-to-Video Q1 converts text prompts into high-quality videos with exceptional visual fidelity and motion diversity. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Vidu Q1 Text-to-Video is a high-end video generation model built on Shengshu Technology’s Vidu Q-series architecture. It transforms natural language prompts into cinematic 720p videos with exceptional realism, diverse motion, and consistent visual fidelity — optimized for creative professionals and production use.

Key Features

• High-Fidelity Generation Produces visually rich, detailed videos with natural lighting, textures, and depth.

• Motion Diversity Captures a wide range of subject and camera motion — from subtle gestures to complex dynamic scenes.

• Temporal Consistency Ensures frame-to-frame coherence and smooth motion transitions without flicker or distortion.

• Prompt-Driven Storytelling Understands complex prompts, generating coherent narrative flow and visual alignment with text.

• Cinematic Quality (720p) Designed for high-quality visual outputs suitable for editing, marketing, and storytelling.

Parameters

• prompt — Describe your desired scene, action, or atmosphere.

• movement_amplitude — Control the motion intensity:

• auto – Adaptive movement based on scene content.

• small – Subtle or static scenes.

• medium – Balanced motion.

• large – Dramatic or action-focused motion.

• style - choose general or anime.

• duration — 5 seconds per generation.

• seed — Optional; set a fixed number for reproducible results.

Pricing

How to Use

1. Write a clear and descriptive prompt explaining the scene.
2. Adjust movement_amplitude to match the desired motion level, and style of your video.
3. (Optional) Set a seed for consistent output.
4. Run the model to generate your 5-second 720p video.

Tips

• Keep prompts concise but descriptive — specify lighting, camera direction, and atmosphere.
• Use medium or large amplitude for cinematic movement.
• Suitable for short-form content, concept visualization, or creative production workflows.

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",
  "movement_amplitude": "auto",
  "style": "general"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/vidu/text-to-video-q1" \
  -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