~Kate Hudson Fanart~ by Ken1171_Designs
Close
Hover over top left image to zoom.
Click anywhere to exit.
Members remain the original copyright holder in all their materials here at Renderosity. Use of any of their material inconsistent with the terms and conditions set forth is prohibited and is considered an infringement of the copyrights of the respective holders unless specially stated otherwise.
Description
Trained my own LoRA model using public photos of Kate Hudson, and then testing it in varied artistic styles, like realistic, semi-realistic, stylized, Anime, cartoon, and illustration. Model trained on Kohya's Python script, images generated in Stable Diffusion. Which is your favorite?
Comments (3)
MollyFootman
Pretty amazing demonstration of AI art. If I am pressed to say which is my favorite, I would go with one of the more "cartoon-y" anime style pictures. Perhaps the one on the bottom row left with the big anime eyes. Thanks for sharing, Ken.
Molly
Ken1171_Designs
Thanks Molly! The most cartoonish are indeed the most intriguing to me too, like the one you picked, and also the 2nd row on the right. ^___^
leeduva
Nice!!!!! Quick question Ken,about the photos of Hudson you use to train with stable diffusion. Were these photos had the same expressions? Or were the pictures of Kate Hudson's had different expressions?
Ken1171_Designs
That's a good question. Most photos were from movie premiere events, where she had mostly the same expressions, but different angles. We can't be picky when using public photos. However, I wasn't worried about that, since I used the same prompt for all images in this post, where she was smiling. In this case, it didn't matter. :)
leeduva
I see,thank you for answering my question:)