FILM (fastforks)
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.
This repo is the model card only: it holds no weights. fastforks downloads the authors' weights from the links below and checks them against the SHA-256 in the model card. Code: https://github.com/kleinicke/fastforks. Kernels for the kernels backend: https://huggingface.co/fastforks/kernels. Original code: https://github.com/dajes/frame-interpolation-pytorch at 33bf477ea2c6.
Task: interpolation. Tier: experimental. Outputs: frame. Backends: portable, kernels.
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].
Variants
Weights are the authors' files (not hosted here). SHA-256 shortened to 12 hex digits; the full hashes are in card.toml.
| variant | weights (author link) | SHA-256 | weights licence | commercial use |
|---|---|---|---|---|
film@1 |
film-net-style-fp32.pt | f810cada26d0 |
Apache-2.0 | yes |
Licence
Original-code strings, recorded as they are (research-use package; check them before any other use). Code: Apache-2.0. Licence files: LICENSE.
Training data: Vimeo-90K (septuplets / triplets for frame interpolation) (google-research/frame-interpolation README "Datasets": Vimeo-90K triplets are the training set (film_net-Style.gin).).
Licence evidence: https://github.com/dajes/frame-interpolation-pytorch/blob/33bf477ea2c65a2ed1b5f2280ee1f02be06910e8/LICENSE ; https://github.com/dajes/frame-interpolation-pytorch/releases/tag/v1.0.2 ; https://github.com/google-research/frame-interpolation/blob/69f8708f08e62c2edf46a27616a4bfcf083e2076/README.md
Input size
any H x W >= 64, padded to a multiple of 64
Tested up to (portable, fp16, RTX 5060 Ti 16 GB): film 1988x2880 (13.0 GiB peak allocated, 15.3 reserved)
Speed and memory
Interpolation, synthetic, 1080x1920
| model | time (ms): original | portable | kernels | kernels speed-up: vs original | vs portable | peak memory (MiB, allocated / reserved): original | portable | kernels |
|---|---|---|---|---|---|---|---|---|
film |
464 | 417 | 333 | 1.4x | 1.3x | 2953 / 3556 | 2856 / 3080 | 2856 / 3060 |
Startup and first call
| model | load (s): original | portable | kernels | first call (s): original | portable | kernels |
|---|---|---|---|---|---|---|
film |
0.29 | 0.43 | 0.65 | 0.95 | 0.42 | 0.33 |
torch.compile and TensorRT
| model | input | time: portable | compile | TensorRT fp16 | kernels | preparation: compile (cold first call) | ONNX + engine build | peak MiB (alloc / reserved): portable | compile | kernels | TensorRT (engine + torch) |
|---|---|---|---|---|---|---|---|---|---|---|---|
film |
1080x1920 | 417 ms | 332 ms | planned for 0.2.1 | 333 ms | 41.1 s | β | 2856 / 3080 | 2666 / 3192 | 2856 / 3060 | β |
Fixed-size cells: time (ms) / peak allocated / peak reserved memory (MiB).
Hardware, protocol and caveats: benchmarks (RTX 5060 Ti 16 GB, sm_120). Original = the original code named above at the precision of portable (fp16, or (fp32) where fp16 is unsupported or not finite); original fp32 = its default fp32 run. Peak memory is the torch allocator's.
Accuracy
On public datasets
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. Original = the original code named under Details, same checkpoint and protocol.
| variant | dataset | original fp32 | original fp16 | portable | kernels | note |
|---|---|---|---|---|---|---|
film |
DAVIS 2017 480p, 2 frame triplets per video (180), PSNR / SSIM | 27.63 / 0.8105 | 27.46 / 0.8092 | 27.63 / 0.8105 | 27.63 / 0.8104 |
Measured on NVIDIA GeForce RTX 5060 Ti, torch 2.14.1+cu130, fastforks d199e94c, 2026-11-14.
Parity with the original code
Every variant is checked against reference outputs of the original code at its pinned commit. 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).
Usage
from fastforks import interpolation
model = interpolation.load("film") # mode="auto": the preferred backend from recorded measurements
result = model("frame1.png", "frame2.png") # timestep=0.5: the middle frame
result.frame # [3, H, W] float32 RGB in [0, 1], input resolution
result.backend # what ran, e.g. Backend(mode='portable', device='cuda:0', dtype='float16')
Install with pip install fastforks (see https://github.com/kleinicke/fastforks). Other variants: film.
Kernels backend
interpolation.load("film", mode="kernels") runs our CUDA kernels (cudnn_hacc). It needs a prebuilt kernel for your GPU architecture (downloaded from https://huggingface.co/fastforks/kernels on first use) and a recent NVIDIA driver; if there is none it raises BackendUnavailableError with the reason and never falls back silently. mode="auto" picks kernels when it can run and logs the choice.