Sign inGet started
Model · Civitai

Felldude/Soft & Fast VAE (SDXL/PONY 80MB Quantized)

Soft Fast VAE (80MB Quantized) VAE was trained and quantized with mixed block precision (F8_E5M2 F8_E4M3) VAE is extremely accurate for quantized VAE The VAE has some saturation increase from BASE SDXL and a softer appearance.

Author / organizationFelldude
Downloads3.9K (as reported by Civitai)
Likes131
Tasktext-to-image
Created8 May 2025
Last updated at source—
text-to-imagevaeponybase modelfp8softgaussian blurquantized
Embed this entry
<iframe src="https://silytics.si/embed/item/8952cf0a-564d-4389-a3fe-9992ef40d9a9" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

Popularity, last 3 days

3,918 now (+4 since 2026-10-15). Counts as reported by the source, snapshotted daily by Silytics.

More from Felldude

Silytics shows public metadata from Civitai and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.