-
Document Intel GPU / NPU / AUTO device support; add --target-device gpu to the export tool
-
Embed playable <video> players for the LR/4x videos in the READMEs; add inline GIF preview
-
Add public-domain NASA video sample: LR vs PyTorch/FP16/INT8/INT4 4x outputs, side-by-side grid, per-frame timings and metrics
-
Add public-domain eagle sample processed by PyTorch + all OpenVINO variants; fix tile padding offset for non-multiple-of-tile sizes
-
benchmark: fall back to Hub download; add sample inputs
-
Add OpenVINO INT4/INT8/FP16 Real-ESRGAN (RealESRGAN_x4plus) models + single-file inference script