PBRify_Remix โ€” ONNX export

ONNX re-exports of the CC0 SPAN models from Kim2091/PBRify_Remix: predict a tangent-space normal map, roughness map, and height map from a single albedo/diffuse texture. All credit for the weights goes to Kim2091.

Exported for QtMeshEditor (issue #404), powering qtmesh material --generate-pbr, the Material Editor's "Generate PBR maps from diffuse" button, the generate_pbr_maps MCP tool, and the PBR stage of the image-to-3D pipeline.

The files QtMeshEditor downloads at runtime live in the shared fernandotonon/QtMeshEditor-models repo (top level). This repo is the standalone model card + mirror.

Files

file output
1x-PBRify_NormalV3.onnx tangent-space normal (RGB)
1x-PBRify_RoughnessV2.onnx roughness (consume as luminance)
1x-PBRify_Height.onnx height/displacement (consume as luminance)

I/O

1ร—3ร—Hร—W float NCHW in [0,1] โ†’ 1ร—3ร—Hร—W out. Dynamic H/W (tile large textures with overlapping tiles + feathered seam blending). Opset 18, ~1.6 MB each.

License & provenance

The upstream repo's LICENSE is CC0-1.0 and its README states the models were trained "exclusively on high quality CC0 content from ambientCG". (OpenModelDB's NormalV3 page lists "ambientCG + UltraSharpV2" as the training set โ€” UltraSharpV2 is cc-by-nc-sa-4.0 โ€” which contradicts the author's own statement; we treat the author's explicit repo LICENSE + "exclusively CC0" statement as authoritative. Documented for transparency.)

Reproducing

scripts/export-pbrify-onnx.py in the QtMeshEditor repo (one-time, offline; spandrel load โ†’ torch.onnx.export, opset 18, dynamic H/W).

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. ๐Ÿ™‹ Ask for provider support