{
  "id": "2211.17115",
  "version": "v1",
  "published": "2022-11-30T15:57:56.000Z",
  "updated": "2022-11-30T15:57:56.000Z",
  "title": "Multiresolution Textual Inversion",
  "authors": [
    "Giannis Daras",
    "Alexandros G. Dimakis"
  ],
  "comment": "Accepted at NeurIPS 2022 Workshop on Score-Based Methods. 5 pages, 4 Figures, work in progress",
  "categories": [
    "cs.CV",
    "cs.AI",
    "cs.LG"
  ],
  "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",
  "revisions": [
    {
      "version": "v1",
      "updated": "2022-11-30T15:57:56.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "multiresolution textual inversion",
      "generate images",
      "extend textual inversion",
      "resolutions",
      "learn pseudo-words"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 5,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}