What is FILM?
The Google-research/frame-interpol is a public API tool that allows users to run models to interpolate frames in large scenes of motion, with a minimum output of 1 and maximum of 8 interpolations per video, at a FPS of 30. The tool presents a single-network approach that achieves state-of-the-art results without using additional pre-trained networks such as optical flow depth. The model is trained with a frame triplet alone and is typically completed within 36 seconds using NVIDIA T4 GPU hardware. Additional information, such as citations and examples, are available on the tool's GitHub page.
FILM pricing Subscription
Language models tokens
$0.65/1m tokens - meta/llama-2-70b
Replicate hardware
$0.000100/sec ($0.36/hr) - 4x - 8gb nvidia t4 gpu
Nvidia a40 (large) gpu predictions
$0.000725/sec ($2.61/hr) - 1x 10x 48gb 72gb nvidia a100 (40gb) gpu
Verify on the official pricing page.
View plansFILM user reviews
Would you recommend FILM?
Recommend this tool?
FILM's key features
-
Interpolate frames in large scenes of motion
-
Single-network approach
-
Achieves state-of-the-art results without using additional pre-trained networks such as optical flow depth
-
Model trained with a frame triplet alone
-
Completed within 36 seconds using nvidia t4 gpu hardware
FILM use cases
-
Enhancing video quality
-
Creating slow-motion effects
-
Improving video compression
Who is it for?
-
Film and video editors
-
Special effects creators
-
Machine learning engineers
-
Ai researchers
-
Data scientists