Model reference · open weights

swin2SR-classical-sr-x2-64

Image caidas Image edit 1 build Open weights 30k dl/mo

swin2SR-classical-sr-x2-64 is an open-weight image model from caidas. swin2SR-classical-sr-x2-64 (FP32) weighs 24 MB; the smallest configuration that runs it is RTX 3060 12 GB.

  • swin2SR-classical-sr-x2-64 is an image-to-image model by caidas designed for image super resolution.
  • It upscales images by a factor of two and contains 12M parameters.
  • The model is released under the apache-2.0 licence.

Summary of the caidas/swin2SR-classical-sr-x2-64 model card, 2026-10-01

What it is

Released bycaidas
Released2022-12-16
Parameters12M
VRAM24 MB for the weights

What it runs on

Memory and cards for swin2SR-classical-sr-x2-64 (FP32)

24 MBweights, file size
5.0 GBworking memory, one 1024² image
537 MBruntime overhead
CardOne imageMemory
RTX 3060 12 GBfits11.6 GB
RTX 4060 Ti 16 GBfits15.4 GB
RTX 3090 24 GBfits23.4 GB
RTX 4090 24 GBfits23.4 GB
RTX 5090 32 GBfits31.0 GB
L40S 48 GBfits44.0 GB
A100 80 GBfits78.2 GB
H100 80 GBfits78.1 GB
RTX PRO 6000 Blackwell 96 GBfits93.8 GB
DGX Spark (GB10) 128 GB unifiedfits107 GB
H200 141 GBfits138 GB
B200 180 GBfits176 GB

From the model card

What caidas says about swin2SR-classical-sr-x2-64

Read the model card

Swin2SR model that upscales images x2. It was introduced in the paper Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration by Conde et al. and first released in this repository.

Intended use cases

This model is intended for image super resolution.

Usage

Refer to the documentation.

Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.

Running it yourself

Run it on a rented GPU

Rent a machine by the hour. How to run this model is on its model card.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms