Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models

Summary:

We use an encoder to personalize a text-to-image model to new concepts with a single image and 5-15 tuning steps.

Abstract:

Text-to-image personalization aims to teach a pre-trained diffusion model to reason about novel, user provided concepts, embedding them into new scenes guided by natural language prompts. However, current personalization approaches struggle with lengthy training times, high storage requirements or loss of identity. To overcome these limitations, we propose an encoder-based domain-tuning approach. Our key insight is that by underfitting on a large set of concepts from a given domain, we can improve generalization and create a model that is more amenable to quickly adding novel concepts from the same domain. Specifically, we employ two components: First, an encoder that takes as an input a single image of a target concept from a given domain, e.g. a specific face, and learns to map it into a word-embedding representing the concept. Second, a set of regularized weight-offsets for the text-to-image model that learn how to effectively ingest additional concepts. Together, these components are used to guide the learning of unseen concepts, allowing us to personalize a model using only a single image and as few as 5 training steps - accelerating personalization from dozens of minutes to seconds, while preserving quality.

Cite the paper:

If you use the contents of this project, please cite our paper.

@misc{gal2023encoderbased,
      title={Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models},
      author={Rinon Gal and Moab Arar and Yuval Atzmon and Amit H. Bermano and Gal Chechik and Daniel Cohen-Or},
      year={2023},
      eprint={2302.12228},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

Image credits: James Boyes, Venus the cat