Pika V2.2 Pikaframes API Documentation
Playground
Try it on WaveSpeedAI!Create precise keyframe-to-video sequences with Pika V2.2 Pikaframes. Upload up to 5 keyframes, set per-transition prompts and durations, and interpolate smooth motion for storyboards, camera moves, and style-consistent animation. Supports total runtimes up to 25 seconds. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Features
Pika V2.2 Pickaframes turns one or more still images into a short, animated video. You provide keyframe images plus a global description, optionally set per-segment transitions, and the model fills in motion, camera moves, and in-between frames for social videos, ads, and simple storyboard clips.
Highlights
- Image-driven animation – Start from 1+ still images and let the model create smooth motion and transitions.
- Timeline control via transitions – Use per-segment durations to decide how long the animation lingers between images.
- Production-ready quality – Supports up to 1080p output for most major platforms.
- Prompt-guided style – A single high-level prompt controls look, atmosphere, and camera behaviour.
Parameters
-
images (required)
-
Upload one or more images or paste URLs.
-
Single image: the model animates around that scene (camera moves, small changes).
-
Multiple images: they act as keyframes; the video evolves from the first to the last in order.
-
prompt (required) Global description of the clip: content, motion, and style. Example: TV screen flickering in a cozy kitchen, soft camera shake, warm cinematic lighting.
-
transitions (optional) A list of segments; each item has:
-
duration – segment length in seconds
-
prompt (optional) – local override or refinement for this segment only
If transitions are provided, total video length is roughly the sum of all durations. If no transitions are set, a 5-second clip is generated by default.
-
resolution Output quality tier, for example 720p or 1080p.
-
seed
-
−1: random each run (exploration).
-
Any fixed integer: reproducible layout and motion.
Output format: MP4 video at the chosen resolution.
Pricing
Pricing is $0.04 per second for 720p or $0.06 per second for 1080p, with a minimum of 5 billable seconds.
| Billable Duration | 720p | 1080p |
|---|---|---|
| 5s | $0.20 | $0.30 |
| 10s | $0.40 | $0.60 |
| 15s | $0.60 | $0.90 |
| 20s | $0.80 | $1.20 |
| 25s | $1.00 | $1.50 |
Billing Rules
- With custom transitions, duration is the sum of all transition durations. An omitted transition duration defaults to 5 seconds.
- Without custom transitions, duration is 5 × (number of images − 1) seconds.
- Total duration is rounded up to the next whole second for billing.
- Supply 2–5 images. Custom transitions must contain exactly one item per adjacent image pair.
- Total transition duration must not exceed 25 seconds. This is an input limit, not automatic truncation.
promptandseeddo not add separate charges.
How to Use
-
Write the global prompt In the prompt field, describe the overall scene and motion in one or two sentences (for example: TV screen flickering, reflections on the counter, slight handheld camera feel).
-
Add images
- Under images, upload at least one frame or paste image URLs.
- Click Add Item to append more keyframes; they are used in order from top to bottom.
- Configure transitions (optional but recommended for multi-image stories)
- In transitions, click Add Item.
- Set duration in seconds for how long the animation should spend between the current and next keyframe.
- Optionally add a local prompt to nudge that segment’s motion or style.
- Add multiple transition items if you want a longer sequence; total length is their duration sum.
- Choose resolution
- Use 720p for quick iteration and previews.
- Switch to 1080p once you are happy with the motion and want a final render.
- Set seed if needed
- Keep −1 when exploring different variations.
- Use a fixed integer when you want to lock in a specific behaviour for future runs.
- Run and download
- Check the estimated cost shown on the Run button (for example, 0.20 USD for 5 seconds at 720p).
- Click Run, wait for processing, then download your generated MP4 from the result panel.
Tips
- Use images with similar aspect ratios to avoid stretching during transitions.
- To mimic flickering or jump cuts, use two very similar images with short transition durations.
- Iterate with short, cheap runs first, then extend durations and upgrade resolution for the final version.
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'
{
"images": [
"https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
],
"resolution": "720p"
}
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/pika/v2.2-pikaframes" \
-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
doneRetry temporary errors only while polling, never the submit request. Errors, retries and timeouts
Parameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| images | array<string> | Yes | - | 2 ~ 5 items | URL of ref images to use while generating the video. |
| prompt | string | No | - | The positive prompt for the generation. | |
| transitions | array<object> | No | - | 0 ~ 5 items | Configuration for each transition. Length must be len(image_urls) - 1. Total duration of all transitions must not exceed 25 seconds. If not provided, uses default 5-second transitions with the global prompt |
| transitions[].duration | number | No | 5 | 5 ~ 25 | Duration of this transition in seconds |
| transitions[].prompt | string | No | - | - | Specific prompt for this transition. Overrides the global prompt if provided. |
| resolution | string | No | 720p | 720p, 1080p | The resolution of the generated video. |
| seed | integer | No | - | - | The random seed to use for the generation. -1 means a random seed will be used. |
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Output values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.status | string | Task status. completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses. |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |
Result Request Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| id | string | Yes | - | Task ID |
Result Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction |
| data.model | string | Model ID used for the prediction |
| data.outputs | array<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.urls | object | Object containing related API endpoints |
| data.status | string | Status: completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses |
| data.created_at | string | ISO timestamp of when the request was created |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |