Browse ModelsWavespeed AIRife Video Interpolation

Rife Video Interpolation

Rife Video Interpolation

Playground

Try it on WavespeedAI!

RIFE Video Interpolation generates smooth intermediate frames between existing video frames for higher frame rates and smoother motion. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Features

RIFE Video Interpolation

RIFE Video Interpolation uses the state-of-the-art Real-Time Intermediate Flow Estimation algorithm to increase your video’s frame rate by inserting synthetic frames between existing ones. The result is dramatically smoother motion — ideal for slow-motion effects, fixing choppy footage, or simply upgrading the visual quality of any clip.


Why Choose This?

  • Smooth, natural motion Synthesized frames blend seamlessly with the original footage, eliminating stutters and judder without ghosting or blurring.

  • Flexible interpolation steps Choose 1 to 4 interpolation frames per original frame pair to dial in exactly the level of smoothness you need.

  • Works on any footage Talking heads, action shots, cinematic scenes, screen recordings — RIFE adapts to a wide range of video content.

  • No local setup Upload, run, and download. No GPU required on your end.


Parameters

ParameterRequiredDescription
videoYesInput video to interpolate (URL or file upload).
num_framesNoNumber of frames to insert between each original frame pair. Options: 1, 2, 3, 4.

How to Use

  1. Upload your video — provide the clip you want to smooth via URL or drag-and-drop.
  2. Set num_frames — choose how many synthetic frames to insert between each original frame pair (1 = mild, 4 = maximum smoothness).
  3. Submit — process, preview, and download your interpolated video.

Pricing

$0.01 per second of input video, with a minimum charge of 1 second.


Best Use Cases

  • Slow-motion effects — Dramatically slow down footage while maintaining smooth, fluid motion.
  • Frame rate upscaling — Convert 24fps footage to a higher effective frame rate for a more cinematic or broadcast-ready feel.
  • Fixing choppy video — Smooth out low-frame-rate recordings from older cameras, screen captures, or compressed sources.
  • Animation smoothing — Increase the fluidity of animated sequences without re-rendering the source.

Pro Tips

  • Higher num_frames values produce smoother results but may introduce subtle artifacts on very fast motion — test with 2 first if your footage has rapid movement.
  • RIFE works best on well-lit, stable footage; heavily compressed or noisy input may produce less clean interpolation.
  • For slow-motion use, shoot at the highest frame rate your camera supports, then interpolate further with RIFE.

Notes

  • video is the only required field.
  • Pricing is based on the duration of the input video at $0.01 per second, with a minimum charge of 1 second.
  • Ensure video URLs are publicly accessible if using a link rather than a direct upload.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result


# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/rife/video-interpolation" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "num_frames": 1
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"

Parameters

Task Submission Parameters

Request Parameters

ParameterTypeRequiredDefaultRangeDescription
videostringYes-The URL of the video to interpolate.
num_framesintegerNo11, 2, 3, 4Number of intermediate frames to generate between each pair of original frames.

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.outputsarrayArray of URLs to the generated content (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.has_nsfw_contentsarrayArray of boolean values indicating NSFW detection for each output
data.statusstringStatus of the task: created, processing, completed, or failed
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, the ID of the prediction to get
data.modelstringModel ID used for the prediction
data.outputsstringArray of URLs to the generated content (empty when status is not completed).
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.statusstringStatus of the task: created, processing, completed, or failed
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
© 2025 WaveSpeedAI. All rights reserved.