Пропустить навигацию
StyleDrop: Text-to-Image Generation in Any Style
0:00 / 1:56

StyleDrop: Text-to-Image Generation in Any Style

AK

@_akhaliq530 тыс. подписчиков

Открыть в X
208 отметок «Нравится»СкачатьОригинальный пост

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)

  • Фото профиля AP

    @angrypenguinPNG

    Imagen about to be OP. Great work @natanielruizg !

    3 отметки «Нравится»

  • Фото профиля 8pm

    @themissingdog

    CSS generation would save a lot of time.

    1 отметка «Нравится»

  • Фото профиля CubanHodLer🇨🇺

    @CubanBTC

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

  • Фото профиля 𝘓𝘶𝘪𝘴 𝘎𝘰𝘮𝘦𝘻-𝘎𝘶𝘻𝘮𝘢𝘯

    @3DSculpts

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

  • Фото профиля Mitchell Stooksbury

    @MitchellStooks

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