trained with 132 images, 50k steps on variable speed
















Inspired by a medium type tag "Architectural Diggest Photo" which is recognized by Stable Diffusion, I researched architectural magazines further and trained this textual inversion to be used as a better version of that medium (example: "archmagazine photo").
Trigger word: archmagazine. Prompt archmagazine photo of or archmagazine 3d render of, etc.
This will help with the composition of the image and will influence colors. It may also navigate toward the Photo medium (data set were photos), but you can always use a strength of 0.5-0.9 if something is too much for you.
It will work best for typical rooms inside the house: Living room, bedroom, bathroom, kitchen, dining room, etc.
Enjoy your image generation and share the results with us in the comments.
trained with 132 images, 50k steps on variable speed
1.転載モデルは学習・共有目的のみで使用し、著作権は原作者に帰属します
2.モデルの認証は公式チャンネルでご連絡ください。クリエイターの権利保護に努めています クリックして認証
