Face0: Instantaneously Conditioning a Text-to-Image Model on a Face

TL;DR

Face0 enables instant, in-sample conditioning of text-to-image models on faces without fine-tuning, allowing quick, flexible face-based image generation and manipulation, potentially reducing biases.

Contribution

Face0 introduces a simple, fast method to condition text-to-image models on faces without optimization, enhancing capabilities and bias mitigation.

Findings

Achieves rapid face-conditioned image generation in seconds.

Allows control via text prompts or face manipulations.

Supports consistent character generation across images.

Abstract

We present Face0, a novel way to instantaneously condition a text-to-image generation model on a face, in sample time, without any optimization procedures such as fine-tuning or inversions. We augment a dataset of annotated images with embeddings of the included faces and train an image generation model, on the augmented dataset. Once trained, our system is practically identical at inference time to the underlying base model, and is therefore able to generate images, given a user-supplied face image and a prompt, in just a couple of seconds. Our method achieves pleasing results, is remarkably simple, extremely fast, and equips the underlying model with new capabilities, like controlling the generated images both via text or via direct manipulation of the input face embeddings. In addition, when using a fixed random vector instead of a face embedding from a user supplied image, our method essentially solves the problem of consistent character generation across images. Finally, while requiring further research, we hope that our method, which decouples the model's textual biases from its biases on faces, might be a step towards some mitigation of biases in future text-to-image models.