DreamAnime: Learning style-identity textual disentanglement for anime and beyond
Publication Type
Journal Article
Publication Date
5-2024
Abstract
Text-to-image generation models have significantly broadened the horizons of creative expression through the power of natural language. However, navigating these models to generate unique concepts, alter their appearance, or reimagine them in unfamiliar roles presents an intricate challenge. For instance, how can we exploit language-guided models to transpose an anime character into a different art style, or envision a beloved character in a radically different setting or role? This paper unveils a novel approach named DreamAnime, designed to provide this level of creative freedom. Using a minimal set of 2-3 images of a user-specified concept such as an anime character or an art style, we teach our model to encapsulate its essence through novel "words" in the embedding space of a pre-existing text-to-image model. Crucially, we disentangle the concepts of style and identity into two separate "words", thus providing the ability to manipulate them independently. These distinct "words" can then be pieced together into natural language sentences, promoting an intuitive and personalized creative process. Empirical results suggest that this disentanglement into separate word embeddings successfully captures a broad range of unique and complex concepts, with each word focusing on style or identity as appropriate. Comparisons with existing methods illustrate DreamAnime's superior capacity to accurately interpret and recreate the desired concepts across various applications and tasks. Code is available at https://github.com/chnshx/DreamAnime.
Keywords
Data Models, Training, Task Analysis, Computational Modeling, Natural Languages, Visualization, Shape, Customization, Diffusion, Image Synthesis, Style Disentanglement
Discipline
Artificial Intelligence and Robotics | Graphics and Human Computer Interfaces
Research Areas
Intelligent Systems and Optimization
Publication
IEEE Transactions on Visualization and Computer Graphics
First Page
1
Last Page
12
ISSN
1077-2626
Identifier
10.1109/TVCG.2024.3397712
Publisher
Institute of Electrical and Electronics Engineers
Citation
XU, Chenshu; XU, Yangyang; ZHANG, Huaidong; XU, Xuemiao; and HE, Shengfeng.
DreamAnime: Learning style-identity textual disentanglement for anime and beyond. (2024). IEEE Transactions on Visualization and Computer Graphics. 1-12.
Available at: https://ink.library.smu.edu.sg/sis_research/9799
Additional URL
https://doi.org/10.1109/TVCG.2024.3397712