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.
â Key features & benefits
FILM core features and benefits include the following:
- âī¸ Interpolate frames in large scenes of motion.
- âī¸ Single-network approach.
- âī¸ Achieves state-of-the-art results without using additional pre-trained networks such as optical flow depth.
- âī¸ Model trained with a frame triplet alone.
- âī¸ Completed within 36 seconds using nvidia t4 gpu hardware.
âī¸ Use cases and applications
- Enhancing video quality.
- Creating slow-motion effects.
- Improving video compression.
đââī¸ Who is it for?
FILM can be useful for the following user groups:
đ° Pricing plans
FILM offers a Subscription pricing model.
FILM pricing packages
- Language models tokens plan : $0.65/1m tokens - meta/llama-2-70b
- Replicate hardware plan : $0.000100/sec ($0.36/hr) - 4x - 8gb nvidia t4 gpu
- Nvidia a40 (large) gpu predictions plan : $0.000725/sec ($2.61/hr) - 1x 10x 48gb 72gb nvidia a100 (40gb) gpu
** Pricing packages are subject to change. Always verify pricing information here
âšī¸ Find more & support
FILM provides an API that developers can use for programmatic access which makes it easy to integrate it with other tools or within your own applications.
You can also find more information, get support and follow FILM updates on the following channels:
- FILM Website (Login/Sign up)
How do you rate FILM?
Breakdown đ