Wan 2.1 I2V 720p Ultra Fast API Documentation

Wan 2.1 I2V 720p Ultra Fast API Documentation

Playground

WAN 2.1 Image-to-Video (i2v) 720P Ultra-Fast converts images into 720P videos with ultra-fast inference and supports unlimited AI video generation for high-throughput workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Wan 2.1 I2V 720p Ultra Fast is a fast image-to-video model that animates a single reference image into a short clip guided by your prompt. It’s optimized for quick turnaround at 720p while keeping the input image as the visual anchor—ideal for rapid storyboarding, motion exploration, and production-friendly iteration.

Key capabilities

• Image-to-video (I2V) generation at 720p
• Strong image anchoring for subject consistency
• Prompt-driven motion and camera direction (follow, dolly, orbit, pan/tilt)
• Tunable motion behavior with guidance and flow controls
• Great for quick drafts, fast iterations, and high-throughput generation

Use cases

• Turn key art into short motion clips for ads, social posts, and previews
• Animate characters and products while keeping the original look
• Test different camera moves (push-in, rise, follow, orbit) from the same image
• Generate multiple motion variants quickly for editing and selection
• Previsualization for longer or higher-cost renders

Pricing

Inputs

• image (required): reference image that anchors subject and composition
• prompt (required): describe action + camera + environment motion
• negative_prompt (optional): suppress artifacts like blur, jitter, distortions

Parameters

• size: output resolution preset (e.g., 1280×720)
• duration: video length (commonly 5s or 10s)
• num_inference_steps: more steps can improve detail and motion stability
• guidance_scale: prompt adherence strength (higher = follows prompt more)
• flow_shift: motion behavior tuning (useful for more/less dynamic motion)
• seed: set for reproducible results (-1 for random)

Prompting guide (I2V)

Write prompts like a shot list:

• Subject + action: what the subject does over time
• Camera movement: “camera rises”, “follows behind”, “slow dolly-in”, “orbit”
• Motion constraints: “smooth motion”, “stable framing”, “no jitter”
• Environment: weather, particles, crowd, lighting shifts for realism

Example prompt

LEGO minifigure snowboarding on a mountain ridge, carving smooth S-turns while staying sideways on the board. The camera starts low in front, then rises and follows as the rider moves left and right across the slope. Snow sprays from the board, wind-blown powder in the air, dynamic action, smooth motion, stable framing, cinematic winter lighting.

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",
  "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
  "size": "1280*720",
  "num_inference_steps": 30,
  "duration": 5,
  "guidance_scale": 5,
  "flow_shift": 5
}
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/wavespeed-ai/wan-2.1/i2v-720p-ultra-fast" \
  -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

Parameters

Task Submission Parameters

Request Parameters

Every model also accepts the global request options enable_sync_mode and enable_base64_output; see their pages for details.

Response Parameters

Result Request Parameters

Result Response Parameters