paper-with-me

홈 › Papers

StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators

2021-08-02 · Rinon Gal, Or Patashnik, Haggai Maron, Gal Chechik, Daniel Cohen-Or

Can a generative model be trained to produce images from a specific domain, guided by a text prompt only, without seeing any image? In other words: can an image generator be trained "blindly"? Leveraging the semantic power of large scale Contrastive-Language-Image-Pre-training (CLIP) models, we present a text-driven method that allows shifting a generative model to new domains, without having to collect even a single image. We show that through natural language prompts and a few minutes of training, our method can adapt a generator across a multitude of domains characterized by diverse styles and shapes. Notably, many of these modifications would be difficult or outright impossible to reach with existing methods. We conduct an extensive set of experiments and comparisons across a wide range of domains. These demonstrate the effectiveness of our approach and show that our shifted models maintain the latent-space properties that make generative models appealing for downstream tasks.

📄 PDF Abstract BibTeX arXiv:2108.00946

Code (3)

rinongal/StyleGAN-nada 공식 구현 pytorch
adriaciurana/exploration-stylegan-nada pytorch
macderru/hyperdomainnet pytorch

Tasks

Domain AdaptationImage Manipulation

Similar Papers 제목 키워드 기반

HyperGAN-CLIP: A Unified Framework for Domain Adaptation, Image Synthesis and Manipulation

2024-11-19 · Abdul Basit Anees, Ahmet Canberk Baykal, Muhammed Burak Kizil, Duygu Ceylan 외

Generative Adversarial Networks (GANs), particularly StyleGAN and its variants, have demonstrated remarkable capabilities in generating highly realistic images. Despite their success, adapting these models to diverse tas…

Domain AdaptationImage GenerationImage ManipulationStyle Transfer

StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery

2021-03-31 · ICCV 2021 10 · Or Patashnik, Zongze Wu, Eli Shechtman, Daniel Cohen-Or 외

Inspired by the ability of StyleGAN to generate highly realistic images in a variety of domains, much recent work has focused on understanding how to use the latent spaces of StyleGAN to manipulate generated and real ima…

Image Manipulation

StyleHumanCLIP: Text-guided Garment Manipulation for StyleGAN-Human

2023-05-26 · Takato Yoshikawa, Yuki Endo, Yoshihiro Kanamori

This paper tackles text-guided control of StyleGAN for editing garments in full-body human images. Existing StyleGAN-based methods suffer from handling the rich diversity of garments and body shapes and poses. We propose…

DiversityImage Generation

Image-Based CLIP-Guided Essence Transfer

2021-10-24 · Hila Chefer, Sagie Benaim, Roni Paiss, Lior Wolf

We make the distinction between (i) style transfer, in which a source image is manipulated to match the textures and colors of a target image, and (ii) essence transfer, in which one edits the source image to include hig…

Domain AdaptationStyle Transfer

CLIP2GAN: Towards Bridging Text with the Latent Space of GANs

2022-11-28 · YiXuan Wang, Wengang Zhou, Jianmin Bao, Weilun Wang 외

In this work, we are dedicated to text-guided image generation and propose a novel framework, i.e., CLIP2GAN, by leveraging CLIP model and StyleGAN. The key idea of our CLIP2GAN is to bridge the output feature embedding …

AttributeImage GenerationSelf-Supervised Learning