0
0

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?

More than 1 year has passed since last update.

Stable Diffusion ControlNetのCanyのLow ThresholdおよびHigh Thresholdの検証

Posted at

ControlNetの輪郭を抽出するCannyというプリプロセッサおよびモデルの検証結果です。
Cannyを利用することで既存の写真と同じ構図の画像を生成することができます。

image.png

結論

  • LowとHighの違いはよくわからなかった
  • Thresholdは高い方が輪郭線の量が減るが、劇的な変化はない

Low Thresholdの値を変えて試してみる

  • High Thresholdはデフォルトの150を使用

Low Threshold:1 最低値

image.png

Low Threshold:100 デフォルト値

image.png

Low Threshold:200

image.png

Low Threshold:255 最高値

image.png

High Thresholdの値を変えて試してみる

  • Low Thresholdはデフォルトの100を使用

High Threshold:1 最低値

image.png

High Threshold:100

image.png

High Threshold:150 デフォルト値

image.png

High Threshold:200

image.png

High Threshold:255 最高値

image.png

0
0
0

Register as a new user and use Qiita more conveniently

  1. You get articles that match your needs
  2. You can efficiently read back useful information
  3. You can use dark theme
What you can do with signing up
0
0

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?