Sign inGet started
Model · Civitai

hakoniwa/ControlNet 852_a_scribble_xl

An anime-trained Scribble ControlNet for SDXL. It is designed to turn rough sketches into finished images, or regenerate drawings and photos while preserving their shapes. Usage Recommended preprocessor: lineart realistic. Use a precise prompt to describe the intended result. Available versions: normal, hard, and veryhard. 日本語 normalとhardとveryhardのバージョンがあります。 このcontrolnetはアニメ調の学習をしたSDXL系列のscribbleモデルです。 落書きを描き上げたり、絵や写真の形状を維持しながら再生成するのに特化しています。 controlnetに入力する画像に適用するプリプロセッサはlineart realisticがおすすめです。 プロンプトは正確に入れたほうが良いです。

Author / organizationhakoniwa
Downloads20.8K (as reported by Civitai)
Likes492
Tasktext-to-image
Created14 May 2024
Last updated at source—
text-to-imagecontrolnetsdxl 1.0tool
Embed this entry
<iframe src="https://silytics.si/embed/item/017e525b-9f16-44a7-a37a-0311c63520a5" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

More from hakoniwa

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 Information may be incomplete or out of date.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.