StyleMC: Multi-Channel Based Fast Text-Guided Image Generation and Manipulation

TL;DR

StyleMC is a rapid, efficient method for text-guided image generation and manipulation using CLIP, requiring only seconds of training per prompt and no prompt engineering, applicable to any pre-trained StyleGAN2.

Contribution

It introduces a fast, universal approach for text-driven image editing that significantly reduces training time and complexity compared to prior CLIP-based methods.

Findings

Requires only a few seconds of training per prompt

Does not need prompt engineering

Effective across various StyleGAN2 models

Abstract

Discovering meaningful directions in the latent space of GANs to manipulate semantic attributes typically requires large amounts of labeled data. Recent work aims to overcome this limitation by leveraging the power of Contrastive Language-Image Pre-training (CLIP), a joint text-image model. While promising, these methods require several hours of preprocessing or training to achieve the desired manipulations. In this paper, we present StyleMC, a fast and efficient method for text-driven image generation and manipulation. StyleMC uses a CLIP-based loss and an identity loss to manipulate images via a single text prompt without significantly affecting other attributes. Unlike prior work, StyleMC requires only a few seconds of training per text prompt to find stable global directions, does not require prompt engineering and can be used with any pre-trained StyleGAN2 model. We demonstrate the effectiveness of our method and compare it to state-of-the-art methods. Our code can be found at http://catlab-team.github.io/stylemc.