HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

Harmonizer

nvidia/Harmonizer

kind
original
quant
bf16 (16-bit)
family
misc
modality
image-to-image
root model
nvidia/Harmonizer
provider
nvidia
license
other
language
en
context
—
library
pytorch
vRAM (GB)
—
size on disk
—
downloads
3,329
likes
22
created
—
last modified
2026-07-21T08:41:40+00:00 (2026)
huggingface
https://huggingface.co/nvidia/Harmonizer
tags
pytorchnvidiaharmonizerimage-to-imagediffusionneural-reconstructiongaussian-splattingnerfphysical-aiautonomous-drivingendataset:nvidia/Harmonizer-Datasetarxiv:2602.24096license:otherregion:us

Benchmark scores (1)

benchmarkcategoryscorecontextconfevidence
QuALITYknowledge31.06Harmonizer: temporal mode<br>(highest output)<br><br>Inference enabled through the following checkpoint:<br>`diffusion_harmonizer.pkl`medium| Harmonizer: temporal mode<br>(highest quality output)<br><br>Inference enabled through the following checkpoint:<br>`diffusion_harmonizer.pkl` | 31.06 | 0.15 | 27.40 |

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.