English

Subject-driven Text-to-Image Generation via Apprenticeship Learning

Computer Vision and Pattern Recognition 2023-10-03 v5 Artificial Intelligence

Abstract

Recent text-to-image generation models like DreamBooth have made remarkable progress in generating highly customized images of a target subject, by fine-tuning an ``expert model'' for a given subject from a few examples. However, this process is expensive, since a new expert model must be learned for each subject. In this paper, we present SuTI, a Subject-driven Text-to-Image generator that replaces subject-specific fine tuning with in-context learning. Given a few demonstrations of a new subject, SuTI can instantly generate novel renditions of the subject in different scenes, without any subject-specific optimization. SuTI is powered by apprenticeship learning, where a single apprentice model is learned from data generated by a massive number of subject-specific expert models. Specifically, we mine millions of image clusters from the Internet, each centered around a specific visual subject. We adopt these clusters to train a massive number of expert models, each specializing in a different subject. The apprentice model SuTI then learns to imitate the behavior of these fine-tuned experts. SuTI can generate high-quality and customized subject-specific images 20x faster than optimization-based SoTA methods. On the challenging DreamBench and DreamBench-v2, our human evaluation shows that SuTI significantly outperforms existing models like InstructPix2Pix, Textual Inversion, Imagic, Prompt2Prompt, Re-Imagen and DreamBooth, especially on the subject and text alignment aspects.

Keywords

Cite

@article{arxiv.2304.00186,
  title  = {Subject-driven Text-to-Image Generation via Apprenticeship Learning},
  author = {Wenhu Chen and Hexiang Hu and Yandong Li and Nataniel Ruiz and Xuhui Jia and Ming-Wei Chang and William W. Cohen},
  journal= {arXiv preprint arXiv:2304.00186},
  year   = {2023}
}

Comments

Accepted at NeurIPS 2023. Model Service to be appear as Google Vertex AI - Instant Tuning (https://cloud.google.com/vertex-ai/docs/generative-ai/image/fine-tune-model). The link to demo video: https://www.youtube.com/watch?v=Q2xQ91D_dhM&t=2071s&ab_channel=GoogleCloud

R2 v1 2026-06-28T09:44:15.170Z