Sign inGet started
Model · Civitai

nucleardiffusion/FIX FP16 Errors SDXL - Lower Memory use! --- sdxl-vae-fp16-fix by madebyollin

"As good as SDXL VAE but runs twice as fast and uses significantly less memory." https://huggingface.co/madebyollin/sdxl-vae-fp16-fix/discussions/7 "Same license on stable-diffusion-xl-base-1.0 same vae license on sdxl-vae-fp16-fix Troubleshoot: Do not use the refiner with VAE built in Try launch param: --medvram --opt-split-attention --xformers SDXL-VAE-FP16-Fix is the [SDXL VAE]( https://huggingface.co/stabilityai/sdxl-vae , but modified to run in fp16 precision without generating NaNs. Details: SDXL-VAE generates NaNs in fp16 because the internal activation values are too big: SDXL-VAE-FP16

Author / organizationnucleardiffusion
Downloads57.8K (as reported by Civitai)
Likes2K
Tasktext-to-image
Created12 January 2024
Last updated at source—
text-to-imagevaesdxl 1.0base modelbasesdxl
Embed this entry
<iframe src="https://silytics.si/embed/item/127c6930-3317-48c3-b428-8b0ad0692fb6" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

More from nucleardiffusion

Silytics shows public metadata from Civitai and links to the original. Information may be incomplete or out of date. Last refreshed 15 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.