Get a weekly rundown of the latest AI models and research... subscribe! https://aimodels.substack.com/

Amt

pollinations

AI model preview image
The AMT model, tagged under Video-to-Video, is a Video Smoother useful for efficient frame interpolation. The model works by transforming video inputs into smoother videos with increased frames per second (fps). The input schema requires the video URL, the model_type parameter set to "amt-l", the desired output video fps, and the number of recursive interpolation passes. The model's output is a URL link to the smoother, interpolated video. It is typically used to improve the visual quality of videos.
Video-to-Video

Pricing

Cost per run
$-
USD
Avg run time
-
Seconds
Hardware
-
Prediction

Creator Models

ModelCostRuns
Musicgen Looper Stereo$?43
Rife Video Interpolation$0.075914,219
Adampi$0.06275,479
3d Photo Inpainting$?5,565
Bark$0.03851,031

Similar Models

Try it!

You can use this area to play around with demo applications that incorporate the Amt model. These demos are maintained and hosted externally by third-party creators. If you see an error, message me on Twitter.

Currently, there are no demos available for this model.

Overview

Summary of this model and related resources.

PropertyValue
Creatorpollinations
Model NameAmt
Description

Video Smoother: AMT All-Pairs Multi-Field Transforms for Efficient Frame In...

Read more ยป
TagsVideo-to-Video
Model LinkView on Replicate
API SpecView on Replicate
Github LinkView on Github
Paper LinkView on Arxiv

Popularity

How popular is this model, by number of runs? How popular is the creator, by the sum of all their runs?

PropertyValue
Runs9,122
Model Rank
Creator Rank

Cost

How much does it cost to run this model? How long, on average, does it take to complete a run?

PropertyValue
Cost per Run$-
Prediction Hardware-
Average Completion Time-