Downloads · 30 days
0
skillsafe-ai/realesrgan-x4plus-anime-6b
realesrgan-x4plus-anime-6b 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…
Downloads · 30 days
0
Access
Public
Updated Sep 22, 2026
Repo size
27.8 MB
Likes
0
Public
Click a slice to open those files.
.onnx27 MB · 97%
From the Hugging Face model README
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.
| Upstream | https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth |
| Upstream SHA-256 / commit | f872d837d3c90ed2e05227bed711af5671a6fd1c9f7d7e91c911a61f155e99da |
| Recipe | recipes/realesrgan-x4plus-anime-6b.yaml — sha256 56cb0c56f6231351a9dc4b16e62e2db686ed74a31b8b18ba20c90e830add5802 |
| Toolchain | Python 3.12.13, torch 2.10.0, onnx 1.23.0, onnxruntime 1.30.0 on Darwin 25.6.0 arm64 |
| Converted | 2026-09-22T03:08:57+00:00 |
| file | class | size | SHA-256 |
|---|---|---|---|
model.onnx | registry | 17.11 MB | 9a029dae374b2cd4c3eb2dbbed857e22e6d785687c767aa12828e7356b9fb378 |
model_fp16.onnx | registry | 8.61 MB | 1777c7dffecdf356c234e3387d456a196ed9b72f9f14ed96bc097b9798b7ddbf |
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.
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 | 3.34e-06 | 4.41e-07 | 125.0 dB |
| fp32 | 80×96 | 2.98e-06 | 4.28e-07 | 125.3 dB |
| fp16 | 64×64 | 7.19e-04 | 1.67e-04 | 73.6 dB |
| fp16 | 80×96 | 1.03e-03 | 1.49e-04 | 74.2 dB |
import * as ort from "onnxruntime-web";
const session = await ort.InferenceSession.create("https://huggingface.co/skillsafe-ai/realesrgan-x4plus-anime-6b/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.
Real-ESRGAN RealESRGAN_x4plus_anime_6B weights and RRDBNet 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.