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

by   Umut Kocasari, et al.

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



There are no comments yet.


page 1

page 5

page 6

page 10

page 11

page 12

page 13

page 14


StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery

Inspired by the ability of StyleGAN to generate highly realistic images ...

Text and Image Guided 3D Avatar Generation and Manipulation

The manipulation of latent space has recently become an interesting topi...

Predict, Prevent, and Evaluate: Disentangled Text-Driven Image Manipulation Empowered by Pre-Trained Vision-Language Model

To achieve disentangled image manipulation, previous works depend heavil...

Conditional Image Generation and Manipulation for User-Specified Content

In recent years, Generative Adversarial Networks (GANs) have improved st...

Fantastic Style Channels and Where to Find Them: A Submodular Framework for Discovering Diverse Directions in GANs

The discovery of interpretable directions in the latent spaces of pre-tr...

Exploring Latent Dimensions of Crowd-sourced Creativity

Recently, the discovery of interpretable directions in the latent spaces...

Discovering Multiple and Diverse Directions for Cognitive Image Properties

Recent research has shown that it is possible to find interpretable dire...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.