Pika V2.1 I2V API Documentation

Pika V2.1 I2V API Documentation

Playground

Pika V2.1 turns images into high-quality videos, supporting multiple output sizes and advanced prompt optimization for precise control. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Transform images into stunning videos with Pika V2.1 — the latest image-to-video model from Pika Labs. This updated version delivers improved motion quality, better temporal consistency, and enhanced visual fidelity for professional-grade video generation.

Looking for faster generation? Try Pika V2.0 Turbo I2V for speed-optimized output.

Why It Looks Great

• Latest version: V2.1 brings improved motion and visual quality over previous versions.
• Enhanced consistency: Better temporal coherence for smoother, more stable videos.
• 720p HD output: Sharp, professional-quality video in landscape or portrait.
• Natural motion: Creates fluid, believable movement from static images.
• Extended duration: Generate up to 10 seconds of video.
• Prompt Enhancer: Built-in tool to refine your motion descriptions.
• Safety Checker: Optional content filtering for appropriate output.

Parameters

How to Use

1. Upload your image — drag and drop or paste a public URL.
2. Write your prompt — describe the motion, action, and atmosphere.
3. Use Prompt Enhancer (optional) — click to enrich your description.
4. Choose size — select landscape (1280×720) or portrait (720×1280).
5. Set duration — choose 5 or 10 seconds.
6. Run — click the button to generate.
7. Download — preview and save your video.

Pricing

Per 5-second billing based on duration.

Size Options

Best Use Cases

• Cinematic Content — Create movie-quality video from still images.
• Social Media Videos — Generate engaging content for any platform.
• Storytelling — Bring emotional moments and narratives to life.
• Marketing & Advertising — Transform product shots into dynamic videos.
• Creative Projects — Add professional motion to photography and artwork.

Example Prompts

• “Woman feeding stray cats in an alley, sunset sky above, cats meowing, urban kindness”
• “Cinematic slow-motion hair flip, wind blowing, golden hour backlight”
• “Ocean waves gently lapping at the shore, peaceful rhythm, ambient motion”
• “Character turns to face camera, subtle expression change, dramatic lighting”
• “Steam rising from hot coffee cup, cozy morning atmosphere, soft focus background”

Model Comparison

Pro Tips for Best Results

• V2.1 excels at temporal consistency — use it for smooth, professional results.
• Describe both subject motion and environmental elements for richer output.
• Include cinematic language: “slow-motion”, “dramatic lighting”, “cinematic”.
• Match orientation to platform: portrait for TikTok/Reels, landscape for YouTube.
• Start with 5-second videos to test, then extend to 10 seconds for final delivery.
• Use V2.1 for final deliverables, V2.0 Turbo for rapid testing.

Notes

• Duration options are 5 or 10 seconds.
• If using a URL, ensure it is publicly accessible.
• Enable Safety Checker for content that will be publicly shared.
• V2.1 delivers improved quality over V2.0 with the same pricing.

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",
  "duration": 5
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/pika/v2.1-i2v" \
  -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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 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|deleted) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters