03 · Model Library

The Model Library

Every model family follows the same three steps: download weights, build an engine, use it. This page covers the families, the one-click presets, and building engines for new resolutions.

Weights → engines

Weights are the neural network itself, downloaded once per family. An engine is that network compiled for your hardware and a specific tile size (CoreML on Apple Silicon). The Model Library's left rail shows each family's state: a green dot means ready; Download weights or Build engine mean there is a step left.

A model family page: weights installed (step 1), build (step 2), and the engines already compiled (step 3).

The model families

RefocusFast, consistent CNN upscaler. Used for the standard 4× pass.
Regenerate-QStreaming, quantized generative upscaler. Adds detail with moderate memory use; the default diffusion model.
Regenerate (beta)The full generative upscaler. Maximum detail, heaviest compute.
Frame interpolationGenerates in-between frames to raise the frame rate.
SegmentationSAM2 object segmentation. Powers masks in the Refine workspace.
Depth estimationMonocular video depth maps. Powers the Focus tool and depth masks.
DenoiseTemporal, flow-aligned video denoiser.

Starter presets

Quick setup installs a smaller set of models that cover the main workflows (Refocus, frame interpolation, segmentation, depth) and run well on machines with less RAM. Full setup adds Regenerate-Q, more Refocus resolutions, and larger model variants. Either preset downloads the weights and builds the engines in one step, with per-item progress. You can keep using the app while it runs.

Starter presets. The checklist shows what is already installed and what will be downloaded and built.

Building engines for new dimensions

Engines are compiled per resolution. If you load a video in the Enhance workflow and no engine matches its shape, build one: open the family, click Build engine, and set the dimensions. The drawer validates as you type (dimensions must divide evenly, and it suggests the nearest valid values) and shows a live log while building. Builds take a few minutes per engine.

The build drawer for Refocus: tile size and frame window. Each family exposes its own options (quantization, model size, variant).

Build options

Tile height / widthThe input tile the engine processes at once. For Refocus, output is 4× the tile. Match your footage: 270×480 for vertical phone video, 480×270 for landscape.
Min / Max framesThe temporal window the engine accepts: how many frames it batches per inference.
Quantize (Regenerate)int8 and palettized variants trade a small amount of quality for smaller, faster engines.
Model size (Segmentation)Tiny through Large. Larger models track objects more accurately but load and run slower.
Variant · Size (Depth)Relative or Metric depth, in Small / Base / Large. Metric gives real distances in meters, which the Focus tool can use.
Overwrite toggleRebuild over an existing engine of the same configuration.
Build engines that match the aspect ratios of the footage you work with, for example 270×480 for vertical phone video and 480×270 for landscape. The Enhance workflow picks the best installed engine automatically (Engine · Auto).

Managing disk space

The rail footer shows the total space used. Engines can be deleted individually from step 3 (trash icon) and rebuilt later. Weights stay installed, so rebuilding an engine does not re-download anything.