20 days ago
-
unify cross-links (both networks + both train repos)
-
embed speed chart + consumer-hardware note
22 days ago
-
add TensorRT builder-option update + exact config
-
embed stability graphs inline instead of linking
23 days ago
-
add SPAN_S fairness A/B update section
26 days ago
-
link the converter Space
27 days ago
-
add links to Space / app / Colab
-
document 2x OTF GAN + patch/batch result
30 days ago
-
restore model card (accidental overwrite) + benchmark update
-
initial NERVE upscale Space (ZeroGPU)
-
add honest 2026-09-22 speed benchmark update
-
document icnr.py dependency in quickstart
-
restore full README (was clobbered by dir upload)
-
examples: replace overview montages with full-resolution (no downscale)
-
link Real-ESRGAN N-vs-H comparisons
-
link NERVE-vs-HEART comparisons
-
document 1:1 crops + inputs
-
examples: add 1:1 native crops + input images
-
correct arch line count
-
reorder sections for reading flow
-
enrich model-card metadata (library_name, tags, dataset)
-
fix ncnn layout note (not fixed-size)
-
rewrite Why section: academic tone, trainer motivation, community credit
-
add 'Why NERVE?' as the second section
-
add structured 'help wanted' section
-
document ncnn usage + what we tested / what we did not
-
soften remaining CoreML claim
-
no unverified claims, CC0 data section, embedded examples
-
simplify trainer quickstart (official converter) + ONNX export config
-
add real-image example comparisons
-
add 4x OTF GAN model + ONNX + ncnn (showcase)
-
add ablation log (docs/ABLATIONS.md) + reference from README
-
add 4x OTF fidelity model + ONNX + ncnn
-
NERVE 1.80M release: models, optimized ONNX, ncnn, configs, arch, README
-
document onnx/ncnn artifacts
-
Upload folder using huggingface_hub
