StyleDrop: Text-to-Image Generation in Any Style
AK
Открыть в X@_akhaliq530 тыс. подписчиков
56 408 просмотров
StyleDrop: Text-to-Image Generation in Any Style
introduce StyleDrop, a method that enables the synthesis of images that faithfully follow a specific style using a text-to-image model. The proposed method is extremely versatile and captures nuances and details of a user-provided style, such as color schemes, shading, design patterns, and local and global effects. It efficiently learns a new style by fine-tuning very few trainable parameters (less than 1% of total model parameters) and improving the quality via iterative training with either human or automated feedback. Better yet, StyleDrop is able to deliver impressive results even when the user supplies only a single image that specifies the desired style. An extensive study shows that, for the task of style tuning text-to-image models, StyleDrop implemented on Muse convincingly outperforms other methods, including DreamBooth and textual inversion on Imagen or Stable Diffusion.
paper page:
5 комментариев
Комментарии из оригинального поста в X (Twitter)

@angrypenguinPNG
Imagen about to be OP. Great work @natanielruizg !
3 отметки «Нравится»

@themissingdog
CSS generation would save a lot of time.
1 отметка «Нравится»

@CubanBTC
Why are you sharing only HG hosted papers and not Arxiv anymore? 🤔

@3DSculpts
So is StableDifusion dead? Is this new method the new path to go?

@MitchellStooks
Now I'm curious why we don't have style transfer for images that's this good yet.
