HF Model & Benchmark Matrix

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

Ace-Step-1.5-ScragVAE

scragnog/Ace-Step-1.5-ScragVAE

kind
gguf
quant
gguf (16-bit)
family
misc
modality
audio-to-audio
root model
ACE-Step/ace-step-v1.5-1d-vae-stable-audio-format
provider
scragnog
license
mit
language
en
context
—
library
diffusers
vRAM (GB)
—
size on disk
—
downloads
2,553
likes
15
created
—
last modified
2026-04-19T08:27:38+00:00 (2026)
huggingface
https://huggingface.co/scragnog/Ace-Step-1.5-ScragVAE
tags
diffuserssafetensorsggufaudiomusicvaeautoencoderace-stepacestepdecoderoobleckmusic-generationaudio-to-audioenbase_model:ACE-Step/ace-step-v1.5-1d-vae-stable-audio-formatbase_model:quantized:ACE-Step/ace-step-v1.5-1d-vae-stable-audio-formatlicense:mitregion:us

Benchmark scores (1)

benchmarkcategoryscorecontextconfevidence
QuALITYknowledge1.5low| Adversarial weight | 0.5 | **1.5** |

Discussions (0)

none scraped.

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