Swin2SR Classical 4x

Model specifications

Scale factor

4x

Precision

q8

Parameters

12.2M · q8

Exact size

21,622,515 bytes

Best for

Clean-source 4x fidelity

License

Apache-2.0

Model architecture and pretrained weights are attributed to caidas/swin2SR-classical-sr-x4-64. The ONNX conversion is hosted at Xenova/swin2SR-classical-sr-x4-64. Distributed under the Apache-2.0 license.

Use the self-hosted file

This is the same same-origin asset requested by WKO AI's studio. Remote model fallback is disabled, so a missing mirror fails explicitly.

import { env, pipeline } from '@huggingface/transformers';

env.allowLocalModels = true;
env.allowRemoteModels = false;
env.localModelPath = '/models/';

const upscale = await pipeline(
  'image-to-image',
  'Xenova/swin2SR-classical-sr-x4-64',
  { dtype: 'q8' }
);
const output = await upscale(image);