This model requires you to accept the Apache 2.0 license terms before download.
Description
Swin2SR Classical ×4 — Swin Transformer V2 image super-resolution model that upscales images 4× while restoring fine detail; the classical-SR variant for clean low-resolution inputs. Apache 2.0.
Tags
At a glance
| Kind | image upscaler |
|---|---|
| Precision | float32 |
| Container size | 47.6 MiB |
| Weights inside | 46.8 MiB |
| Components | 1 |
| Licence | Apache 2.0 |
| Origin | caidas/swin2SR-classical-sr-x4-64 @ c69ef3e2d2ac |
What is inside the container
A .nbx container packs every part of swin2SR-classical-sr-x4-64 — its single component with weights, graphs and runtime settings — so one file is all the runtime needs.
| Component | Blocks | Layers | Weights |
|---|---|---|---|
| model | 0 | — | 46.8 MiB |
Memory needed
The weights of swin2SR-classical-sr-x4-64 take 46.8 MiB in float32. That is the floor for the memory the runtime has to place, spread over the devices it finds; activations come on top and grow with the size and length you ask for. A measured peak per device class is not published for this model yet.
Verify what you downloaded
Every download carries its SHA-256, and the file endpoint sends it in the X-NBX-SHA256 header. The container is 47.6 MiB (49,910,048 bytes).
$ sha256sum swin2SR-classical-sr-x4-64.nbx
ead9a5533ae4a13e869f0b2c9a13e236f6609fa6f15ce82272d2816422b5a14c
Questions
What is swin2SR-classical-sr-x4-64?
A image upscaler by caidas, distributed as a float32 .nbx container and licensed Apache 2.0.
How big is the download?
47.6 MiB, of which 46.8 MiB are weights.
How do I run it?
Install the runtime from the download page, then use the commands under “CLI Usage” below: neurobrix import caidas/swin2SR-classical-sr-x4-64, then neurobrix serve --model swin2SR-classical-sr-x4-64.
CLI Usage
$ neurobrix import caidas/swin2SR-classical-sr-x4-64
$ neurobrix serve --model swin2SR-classical-sr-x4-64
$ neurobrix run --prompt "your prompt here"
$ neurobrix stop