1. [Publications](/publications)
2. StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators
 
 # StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators

  ![](/sites/default/files/styles/wide/public/publications/styleGAN-NADA.png?itok=fdsGfTH_)

 > 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.



 ## Authors



Rinon Gal (NVIDIA)

Or Patashnik (Tel-Aviv University)

[Haggai Maron](/person/haggai-maron)

Amir Bermano (Tel-Aviv University)

[Gal Chechik](/person/gal-chechik)

Daniel Cohen-Or (Tel-Aviv University)

 

 

 ## Publication Date



Wednesday, May 4, 2022

 

 ## Published in



[SIGGRAPH 2022](https://s2022.siggraph.org/)

 

 ## Research Area



[Artificial Intelligence and Machine Learning ](/research-area/machine-learning-artificial-intelligence)

[Computer Graphics](/research-area/computer-graphics)

[Generative AI](/research-area/generative-ai)

 

 

 ## External Links



[Project page](https://nvlabs.github.io/StyleGAN-NADA/)