Scalable GANs with Transformers

ICLR 2026 Conference Submission25155 Authors

Keywords: Generative Model, Generative Adversarial Network, Scalable Generative Models

TL;DR: Scalable GANs with transformer achieves state-of-the-art on 1-step class-conditional generation on ImageNet-256

Abstract:

Scalability has driven recent advances in generative modeling, yet its principles remain underexplored for adversarial learning. We investigate the scalability of Generative Adversarial Networks (GANs) through two design choices that have proven to be effective in other types of generative models: training in a compact Variational Autoencoder latent space and adopting purely transformer-based generators and discriminators. Training in latent space enables efficient computation while preserving perceptual fidelity, and this efficiency pairs naturally with plain transformers, whose performance scales with computational budget.
Building on these choices, we analyze failure modes that emerge when naively scaling GANs.
Specifically, we find issues as underutilization of early layers in the generator and optimization instability as the network scales. Accordingly, we provide simple and scale-friendly solutions as lightweight intermediate supervision and width-aware learning-rate adjustment. Our experiments show that GAT, a purely transformer-based and latent-space GANs, can be easily trained reliably across a wide range of capacities (S through XL). Moreover, GAT-XL/2 achieves state-of-the-art single-step, class-conditional generation performance (FID of 2.96) on ImageNet-256 in just 40 epochs, 6× fewer epochs than strong baselines.

Primary Area: generative models

Submission Number: 25155