Downloads · 30 days
0
realesr-general-x4v3
skillsafe-ai/realesr-general-x4v3
realesr-general-x4v3 is a machine learning model from skillsafe-ai. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as bsd-3-clause.
Browser-ready onnx 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 r…
Access
Public
Updated Sep 22, 2026
Repo size
8.1 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx7.3 MB · 90%
At a glance
- License
- bsd-3-clause
- Access
- Public
- Created
- Sep 22, 2026
- Updated
- Sep 22, 2026
- SHA
- 042a40bc
Model card
From the Hugging Face model README
Real-ESRGAN general x4 v3 (SRVGGNetCompact)
Browser-ready onnx 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://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-x4v3.pth |
| Upstream SHA-256 / commit | 8dc7edb9ac80ccdc30c3a5dca6616509367f05fbc184ad95b731f05bece96292 |
| Recipe | recipes/realesr-general-x4v3.yaml — sha256 bc93d30609e3b981c4c61bec23b2c8df737241e9ed64aa99879b21949579fc4f |
| Toolchain | Python 3.12.13, torch 2.10.0, onnx 1.23.0, onnxruntime 1.30.0 on Darwin 25.6.0 arm64 |
| Converted | 2026-09-22T03:08:55+00:00 |
Files
| file | class | size | SHA-256 |
|---|---|---|---|
model.onnx | registry | 4.64 MB | a946f7a9397021b9b6b7e71df3d2821b04cc09ff244423b7ca79cb191ce4a00e |
model_fp16.onnx | registry | 2.33 MB | 8dedfc4b8916f2426111561351bbd3c35d674214a3f5bc28190084cd15133a67 |
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
ONNX Runtime (CPU) output vs the PyTorch reference on a seeded uniform input, thresholds from the recipe ({"fp32": {"max_abs": 0.0001}, "fp16": {"max_abs": 0.05, "psnr_db": 45}}):
| variant | input | max abs | mean abs | PSNR |
|---|---|---|---|---|
| fp32 | 64×64 | 4.41e-06 | 4.91e-07 | 123.8 dB |
| fp32 | 80×96 | 4.11e-06 | 4.99e-07 | 123.7 dB |
| fp16 | 64×64 | 1.82e-03 | 2.81e-04 | 68.6 dB |
| fp16 | 80×96 | 1.78e-03 | 2.77e-04 | 68.8 dB |
Use in the browser
import * as ort from "onnxruntime-web";
const session = await ort.InferenceSession.create("https://huggingface.co/skillsafe-ai/realesr-general-x4v3/resolve/main/model.onnx", { executionProviders: ["webgpu", "wasm"] });
const out = await session.run({ input: new ort.Tensor("float32", pixels, [1, 3, h, w]) });
Contract: input input float32 ['batch', 3, 'height', 'width'] → output output float32 ['batch', 3, 'height_x4', 'width_x4']. Opset 17.
Licence and attribution
Real-ESRGAN realesr-general-x4v3 weights and SRVGGNetCompact architecture: Copyright (c) 2021, Xintao Wang. BSD 3-Clause License. https://github.com/xinntao/Real-ESRGAN
Licence: BSD-3-Clause — notice: https://github.com/xinntao/Real-ESRGAN/blob/a4abfb2979a7bbff3f69f58f58ae324608821e27/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.
- License
- bsd-3-clause
- Created
- Sep 22, 2026
- Updated
- Sep 22, 2026