Real-ESRGAN general x4v3 (ONNX, denoise 0.5)

ONNX export of Real-ESRGAN realesr-general-x4v3 (SRVGGNetCompact, 4x) by Xintao Wang et al., BSD 3-Clause (see LICENSE). Upstream: https://github.com/xinntao/Real-ESRGAN

Built from the official release checkpoints realesr-general-x4v3.pth (sha256 8dc7edb9ac80ccdc30c3a5dca6616509367f05fbc184ad95b731f05bece96292) and realesr-general-wdn-x4v3.pth (sha256 1641f8c4464b9f097c9fdda5589273713f67cf59f3d909e0bd688f0cee269dca), blended 50/50 exactly as the official inference_realesrgan.py does at its default --denoise_strength 0.5.
Input input float32 [1, 3, h, w] RGB 0..1; output output float32 [1, 3, 4h, 4w] (clip to 0..1).
Opset 17. realesr-general-x4v3-dn50.onnx sha256 152a44621a7906878d0a580c0347e8bcce78bafeb949af99383fba13e81f253a.

Used by the techyCoderWorld photo editor, which runs it in the visitor's browser (ONNX Runtime Web).

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support