An old AI architecture shows off some new tricks



summary
Summary

GigaGAN shows that Generative Adversarial Networks are far from obsolete and could be a faster alternative to Stable Diffusion in the future.

Current generative AI models for images are diffusion models trained on large datasets that generate images based on text descriptions. They have replaced GANs (Generative Adversarial Network), which were widely used in the past, as they outperformed them in the quality of generated images for the first time in 2021.

However, GANs are much faster to synthesize pictures and their structure makes them easier to control. Models such as StyleGAN were practically the standard before the breakthrough of diffusion models.

Now, with GigaGAN, researchers from POSTECH, Carnegie Mellon University, and Adobe Research demonstrate a billion-parameter GAN model that, like Stable Diffusion, DALL-E 2, or Midjourney, has been trained on a large dataset and is capable of text- to-image synthesis.

ad

GigaGAN is significantly faster than Stable Diffusion

GigaGAN is six times larger than the largest GAN to date and was trained by the team using the LAION-2B dataset of over 2 billion image-text pairs and COYO-700M. An upscaler based on GigaGAN was trained using Adobe Stock photos.

According to the paper, this scaling is only possible through architectural changes, some of which are inspired by diffusion models.

GigaGAN is a text-to-image model. However, the quality of the images is still somewhat behind those of diffusion models. | Image: Kang et al.

After training, GigaGAN is able to generate 512 x 512 pixel images from text descriptions. The content is clearly recognizable, but does not yet reach the quality of high-quality diffusion models in the examples provided.

On the other hand, GigaGAN is between 10 and 20 times faster than comparable diffusion models: On an Nvidia A100, GAN generates an image in 0.13 seconds, Muse-3B takes 1.3 seconds and Stable Diffusion (v.1.5) 2.9 seconds.

Scaling up to larger models also promises to improve quality, so expect much bigger – and better – GANs in the future.

Recommendation

GigaGAN project page.

Leave a Comment

Your email address will not be published. Required fields are marked *

Scroll to Top