Models · Frame interpolation

FILM

FILM (Reda et al., Google, ECCV 2022): makes the middle frame between two video frames, also for large motion, from a flow pyramid in both directions and features shared across scales. Apache-2.0 code and weights.

experimental Fork of dajes/frame-interpolation-pytorch@33bf477 · backends: portable, kernels

Checkpoint film

Paper 2022 Added in 0.2.0 Evaluated with 0.2.0

Kernels, RTX 5060 Ti 16 GB 332 ms 1080x1920, fp16
vs the faster original 1.4× original fp16: 464 ms
Peak memory 2,856 MiB original: 2,953 MiB
Accuracy vs original fp32 ±0.00 kernels psnr, DAVIS 2017 480p (27.63 original)

Use it

pip install fastforks

Lean install with only what this model needs: pip install fastforks-core

from fastforks import interpolation

model = interpolation.load("film")  # kernels on a supported GPU, else portable PyTorch
result = model(frame1, frame2)
result.frame
result.backend  # what ran: mode, device, dtype, kernels
fastforks bench film

Times the model on this machine. load(…, mode="portable") or mode="kernels" picks a backend; usage guide.

Speed and memory

Every backend on one GPU (RTX 5060 Ti 16 GB) and the same input, the authors’ code included. Kernels runs fp16. Portable runs fp16 on CUDA.

BackenddtypeTime per call (ms)vs original fp16Peak memory
allocated / reserved
Load (s)First call (s)
Original fp32fp32not measured ––––
Original fp16the authors' mixed-precision option (float16); the TorchScript release as inference.py, dt 0.5, zero pad to 64 (centred), --fp16: model.half()fp16 464–2,953 MiB/3,556 MiB0.20.47
Portable fp32fp32not measured ––––
Portablefp16 4171.1×2,856 MiB/3,080 MiB0.40.42
Kernelsfp16 3321.4×2,856 MiB/3,080 MiB0.70.33
Portable + torch.compile 3321.4×2,666 MiB/3,192 MiB41 (build)–
TensorRT fp16fp16 1892.4×2,586 MiBenginenot comparable203 (build)–

Measured on RTX 5060 Ti 16 GB, torch 2.14.1+cu130, 2026-11-14 to 2026-11-16. First call, 3 warm-up, peak reset, median of 3 rounds x median of 5. Ratios divide two times of this table (same GPU, same input). Original fp16 is the authors’ own precision option, else torch.autocast. torch.compile and TensorRT: build time instead of load time. TensorRT memory (engine, not comparable) is the GPU memory the engine took, read from the driver because TensorRT allocates outside PyTorch, so it can't be compared with the PyTorch peaks of the other rows.

Other devices

DeviceBackenddtypems / callPeak memoryOutput vs referenceInput
Apple M1 Pro 16 GB MPS, torch 2.14.1, 2026-11-14Originalfp3210448 12.5 GiB process–1080x1920
Portablefp16out of memory–1080x1920
Portablefp32out of memory–1080x1920
Kernelsfp16not implemented–1080x1920

CUDA memory is torch’s peak allocated / reserved; Apple has no such counter, so the Mac rows show the process footprint (weights, Python and torch included). “Output vs reference” compares the device’s output with the stored golden output under the card’s tolerance; – = not checked on that device. Kernels “not implemented” = no kernels for this model on that backend yet: it runs portable there.

Licence and weights

Commercial use allowed

Code
Apache-2.0 LICENSE
Weights
Apache-2.0 source
Training data

Our reading of the licences, not legal advice.

Weights

film-net-style-fp32.pt 138 MB· hosted on GitHub

fastforks downloads and checks these files on first use (fastforks download film).

Accuracy

The test set through the authors’ code and through ours: same checkpoint, same protocol. The distance between the original’s fp32 and fp16 runs is what half precision alone costs; our runs should stay within it.

DAVIS 2017 480p

2 frame triplets per video (180), PSNR / SSIM

Rundtypepsnr ↑ssim ↑Δ psnr vs fp32 originaltripletsms / triplet
Original fp32fp3227.630.8105 reference 180 –
Original fp16fp1627.460.8092 −0.17 180 –
Portable fp32not measured
Portablefp1627.630.8105 ±0.00 180 –
Kernelsfp1627.630.8104 ±0.00 180 –

DAVIS 2017 trainval 480p (JPEG), frames 0 / 2 and 20 / 22 of each of the 90 videos give the frame 1 / 21 at time 0.5, compared with the real one: PSNR and SSIM (Gaussian 11 x 11, sigma 1.5) of the output rounded to uint8, on RGB in [0, 1], averaged over the triplets for the 180-triplet benchmark. Original = the authors’ code, same checkpoint and protocol. Measured on original fp32, original fp16: RTX 5060 Ti, torch 2.14.1+cu130, 2026-11-14; portable, kernels: RTX 5060 Ti, torch 2.14.1+cu130, fastforks d199e94c, 2026-11-14.

DAVIS 2017

the first triplet per video resized to 1080p (90), PSNR

Rundtypepsnr ↑ssim ↑tripletsms / triplet
Original fp32not measured
Original fp16not measured
Portable fp32not measured
Portablefp1628.71– 90 –
Kernelsnot measured

The original code was not run on this dataset, so the table cannot show the distance to it.

DAVIS 2017 trainval 480p (JPEG), frames 0 / 2 and 20 / 22 of each of the 90 videos give the frame 1 / 21 at time 0.5, compared with the real one: PSNR and SSIM (Gaussian 11 x 11, sigma 1.5) of the output rounded to uint8, on RGB in [0, 1], averaged over the triplets for the 180-triplet benchmark. The fixed 1080p validation resizes the first three frames of each DAVIS video with bilinear interpolation and measures RGB PSNR before rounding the predicted middle frame. Measured on RTX 5060 Ti, torch 2.14.1+cu130, fastforks e3abc519, 2026-11-17.

Closeness to the original

Beyond the test-set scores: the raw output of ours against the original’s fp32 output on the same input, pixel by pixel. CPU, float32: max |diff| <= 5e-05 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 0.001 and p99 <= 0.005 (absolute error of the output frame).

CheckToleranceMeasured
CPU fp32, max |diff|≤ 0.00005 not recorded
GPU default dtypes, mean |diff|≤ 0.001 0.00034
GPU default dtypes, p99 |diff|≤ 0.005 0.00154

Recorded for film on RTX 5060 Ti, torch 2.14.1+cu130, 2026-11-14, with these kernels: cudnn_hacc

Details

FILM (Reda et al., ECCV 2022): frame interpolation for large motion, the authors' film_net with the Style weights (the published default) as dajes/frame-interpolation-pytorch ports it. A 7-level image pyramid of both frames, cascaded features (one convolutional sub-tree extractor shared by all levels, so the coarse levels learn from fine training samples), a residual flow pyramid in both directions with one predictor shared by the coarse levels, both frames' images and features warped to the time on the 5 finest levels, and a U-Net-like decoder. Trained for the middle frame; other times run as upstream allows.

Input / output
Input: two RGB images (consecutive frames). Output: the frame between them at timestep (0.5 by default; 0 = the first, 1 = the second), RGB in [0, 1].
Input size
any H x W >= 64, padded to a multiple of 64; tested up to 1988x2880 (13.0 GiB allocated)
Options
  • cuda_graphs=true
Outputs
frame
CUDA kernels
  • cudnn_haccconvolutions with fp16 accumulation (cuDNN)
Apple (MPS)
fp32, fp16
Full reference, generated from the repository

FILM (Reda et al., Google, ECCV 2022): makes the middle frame between two video frames, also for large motion, from a flow pyramid in both directions and features shared across scales. Apache-2.0 code and weights.

Commercial use: yes.

variantinputbackendtime (ms)peak memory (MiB, allocated / reserved)
filmsynthetic (1080x1920)original
portable
kernels
portable + torch.compile
TensorRT fp16
464
417
332
332
189
2953 / 3556
2856 / 3080
2856 / 3080
2666 / 3192
2658 / 2658
Details

Measured

DAVIS 2017 trainval 480p (JPEG), frames 0 / 2 and 20 / 22 of each of the 90 videos give the frame 1 / 21 at time 0.5, compared with the real one: PSNR and SSIM (Gaussian 11 x 11, sigma 1.5) of the output rounded to uint8, on RGB in [0, 1], averaged over the triplets for the 180-triplet benchmark. The fixed 1080p validation resizes the first three frames of each DAVIS video with bilinear interpolation and measures RGB PSNR before rounding the predicted middle frame. Original = the original code named under Details, same checkpoint and protocol.

variantdatasetoriginal fp32original fp16portablekernelsTensorRTnote
filmDAVIS 2017 480p, 2 frame triplets per video (180), PSNR / SSIM27.63 / 0.810527.46 / 0.809227.63 / 0.810527.63 / 0.8104
filmDAVIS 2017, the first triplet per video resized to 1080p (90), PSNR28.71 / –28.71 / –

Measured on portable: NVIDIA GeForce RTX 5060 Ti, torch 2.14.1+cu130, fastforks d199e94c / e3abc519, 2026-11-14 to 2026-11-17; kernels: NVIDIA GeForce RTX 5060 Ti, torch 2.14.1+cu130, fastforks d199e94c, 2026-11-14; tensorrt: NVIDIA GeForce RTX 5060 Ti, torch 2.14.1+cu130, fastforks e3abc519, 2026-11-17.

Parity

CPU, float32: max |diff| <= 5e-05 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 0.001 and p99 <= 0.005 (absolute error of the output frame).

variantkernels error vs original, mean / p99GPU, torchkernels used
film0.00034 / 0.00154RTX 5060 Ti, torch 2.14.1+cu130cudnn_hacc@cudnn92400

Example output

No example rendered for this checkpoint yet.