Modelpublic

skillsafe-ai/swin2sr-classical-sr-x2-64

sourceHugging Faceapache-2.0updated 4d agoView on Hugging Face

0likes18downloads

Model Card

Swin2SR classical super-resolution x2 (transformers.js)

Browser-ready import artifacts for image-super-resolution, produced by SkillSafe's reproducible converter (`models/` in skillsafe.ai) from a pinned upstream source. Every byte here is derivable from that source plus the recipe below; nothing was edited by hand.

Provenance


Upstream	https://huggingface.co/Xenova/swin2SR-classical-sr-x2-64/tree/93dfc9089abda257351d3a58d5771e2c1ff69442
Upstream SHA-256 / commit	`93dfc9089abda257351d3a58d5771e2c1ff69442`
Recipe	`recipes/swin2sr-classical-sr-x2-64.yaml` — sha256 `c39f5e190a7f4f200ad1b09e8321b097a3202915619bd3faea1c4a3ca9547bcf`
Toolchain	Python 3.12.13, torch 2.10.0, onnx 1.23.0, onnxruntime 1.30.0 on Darwin 25.6.0 arm64
Converted	2026-09-22T21:51:09+00:00

Files

file	class	size	SHA-256
`config.json`	bundle	0.00 MB	`e9ff87b27272c528232332f9c9d454d899940def893d3b53e3b76ef0b486a59f`
`onnx/model.onnx`	registry (fp32)	51.91 MB	`6dde3fe2440543ccae7c40d175609f83c18aeaa3d8456745c4329ef97ae744bd`
`preprocessor_config.json`	bundle	0.00 MB	`cbc36266fcc93d5bc1e9ca69bcc648ae9d268918ad14cd3507216740f129cc4d`

registry files are parameter files served from models.skillsafe.ai once vetted; bundle files ship inside an app; registry-shared is a runtime library reused by every model of the same architecture.

Verification

Imported as published upstream (no conversion). Each file is pinned by SHA-256 to its source; every ONNX file passed onnx.checker and a CPU smoke run under onnxruntime with zero-filled inputs at the declared shapes:

file	inputs	outputs	ms
`onnx/model.onnx`	pixel_values[1, 3, 64, 64]	reconstruction[1, 3, 128, 128]	205.3

Use in the browser

import * as ort from "onnxruntime-web";
const session = await ort.InferenceSession.create("https://huggingface.co/skillsafe-ai/swin2sr-classical-sr-x2-64/resolve/main/onnx/model.onnx", { executionProviders: ["webgpu", "wasm"] });

Contract (onnx/model.onnx): input pixel_values float32 ['batch_size', 'num_channels', 'height', 'width'] → output reconstruction float32 ['batch_size', 'num_channels', 'height', 'width']. Opset 11.

Licence and attribution

Swin2SR: Marcos V. Conde et al., Apache License 2.0 (https://huggingface.co/caidas/swin2SR-classical-sr-x2-64); ONNX export by Xenova.

Licence: Apache-2.0 — notice: https://github.com/mv-lab/swin2sr/blob/main/LICENSE. The conversion recipe and this model card are part of the SkillSafe repository and carry its licence; the weights remain under the upstream licence above.

The full manifest.json in this repo records the recipe, sources, toolchain (including the uv.lock hash) and per-file verification numbers.