Sign inGet started
Model · Civitai

Aegor/Hana Uzaki TI

Decided to make a hana uzaki TI which was trained on 400 images from the anime at 10k steps. Works best when you put masterpiece, best quality and even ultra quality in the positive prompt. Images were made using anything-v4.5-pruned prompt to generate character: hana_uzaki Copy the file to stable-diffusion-webui/embeddings

Author / organizationAegor
Downloads2.3K (as reported by Civitai)
Likes280
Tasktext-to-image
Created27 January 2023
Last updated at source—
text-to-imagetextualinversionotheranimehana uzakiembeddinguzakicharactertextual inversion
Embed this entry
<iframe src="https://silytics.si/embed/item/92bf2363-157d-4149-a64f-055f5552aac0" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

More from Aegor

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 Information may be incomplete or out of date.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.