Sign inGet started
Model ยท Civitai

Pitpe11/SharpSpectrumVAE

Now in XL too! I made this VAE because other VAEs started giving me disappointing results with recent Base Models. This VAE is supposed to match Kl-f8-anime2 or surpass it, depending on the situation. Try it out and see if this works for you.๐Ÿ˜Š Added fp16, bf16, fp32 .safetensors versions. (27/11/23) From my testing, I have found: Clearer details, especially in the eyes. Less hard edges. No distortions. txt2img (no Hires) also gives better results, with hires of course being even better. All versions have the same results. Use what you need for your system. ๐Ÿ˜Š Also check out the suggested reso

Author / organizationPitpe11
Downloads5.8K (as reported by Civitai)
Likes295
Tasktext-to-image
Created27 November 2023
Last updated at sourceโ€”
text-to-imagevaesd 1.5sharpcleanphotorealisticanimestyle
Embed this entry
<iframe src="https://silytics.si/embed/item/1a4e8b17-de0a-463f-a79e-b2738b814178" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

Popularity, last 2 days

5,808 now. Counts as reported by the source, snapshotted daily by Silytics.

More from Pitpe11

Silytics shows public metadata from Civitai and links to the original. Information may be incomplete or out of date. Last refreshed 16 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.