# InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuning

Source: [InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuning](<https://www.sota2.com/research/paper/68fa6f091e209131cea4376a>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T04:28:29.820Z

Authors: Jing Shi, Wei Xiong, Zhe Lin, Hyun Joon Jung

Published: 2023-04-06T23:26:38.000Z

## Abstract

Recent advances in personalized image generation allow a pre-trained text-to-image model to learn a new concept from a set of images. However, existing personalization approaches usually require heavy test-time finetuning for each concept, which is time-consuming and difficult to scale. We propose InstantBooth, a novel approach built upon pre-trained text-to-image models that enables instant text-guided image personalization without any test-time finetuning. We achieve this with several major components. First, we learn the general concept of the input images by converting them to a textual token with a learnable image encoder. Second, to keep the fine details of the identity, we learn rich visual feature representation by introducing a few adapter layers to the pre-trained model. We train our components only on text-image pairs without using paired images of the same concept. Compared to test-time finetuning-based methods like DreamBooth and Textual-Inversion, our model can generate competitive results on unseen concepts concerning language-image alignment, image fidelity, and identity preservation while being 100 times faster.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Personalized Image Generation on Person category](<https://www.sota2.com/research/sota/personalized-image-generation-on-person-category.md>): Personalized Image Generation; Person category; Alignment Score: 0.314.

- [Personalized Image Generation on person category (test)](<https://www.sota2.com/research/sota/personalized-image-generation-on-person-category-test.md>): Personalized Image Generation; person category (test); Quality Score: 3.89.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2304.03411>)

[PDF](<https://arxiv.org/pdf/2304.03411.pdf>)

[Implementation](<https://jshi31.github.io/InstantBooth/>)