Multiresolution Textual Inversion

November 30, 2022 · Entered Twilight · 🏛 arXiv.org

Repo contents: .gitignore, LICENSE, README.md, images, pipeline.py, requirements.txt, scrape_images.py, train_dreambooth.py, train_textual_inversion.py

Authors Giannis Daras, Alexandros G. Dimakis arXiv ID 2211.17115 Category cs.CV: Computer Vision Cross-listed cs.AI, cs.LG Citations 36 Venue arXiv.org Repository https://github.com/giannisdaras/multires_textual_inversion ⭐ 99 Last Checked 1 month ago

Abstract

We extend Textual Inversion to learn pseudo-words that represent a concept at different resolutions. This allows us to generate images that use the concept with different levels of detail and also to manipulate different resolutions using language. Once learned, the user can generate images at different levels of agreement to the original concept; "A photo of $S^*(0)$" produces the exact object while the prompt "A photo of $S^*(0.8)$" only matches the rough outlines and colors. Our framework allows us to generate images that use different resolutions of an image (e.g. details, textures, styles) as separate pseudo-words that can be composed in various ways. We open-soure our code in the following URL: https://github.com/giannisdaras/multires_textual_inversion