Scaling up GANs for Text-to-Image Synthesis
About
The recent success of text-to-image synthesis has taken the world by storm and captured the general public's imagination. From a technical standpoint, it also marked a drastic change in the favored architecture to design generative image models. GANs used to be the de facto choice, with techniques like StyleGAN. With DALL-E 2, auto-regressive and diffusion models became the new standard for large-scale generative models overnight. This rapid shift raises a fundamental question: can we scale up GANs to benefit from large datasets like LAION? We find that na\"Ively increasing the capacity of the StyleGAN architecture quickly becomes unstable. We introduce GigaGAN, a new GAN architecture that far exceeds this limit, demonstrating GANs as a viable option for text-to-image synthesis. GigaGAN offers three major advantages. First, it is orders of magnitude faster at inference time, taking only 0.13 seconds to synthesize a 512px image. Second, it can synthesize high-resolution images, for example, 16-megapixel pixels in 3.66 seconds. Finally, GigaGAN supports various latent space editing applications such as latent interpolation, style mixing, and vector arithmetic operations.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Image Generation | ImageNet 256x256 (val) | FID3.45 | 307 | |
| Class-conditional Image Generation | ImageNet 256x256 (train) | IS225.5 | 305 | |
| Class-conditional Image Generation | ImageNet 256x256 (val) | FID3.45 | 293 | |
| Image Generation | ImageNet 256x256 | FID3.45 | 243 | |
| Class-conditional Image Generation | ImageNet 256x256 (train val) | FID3.45 | 178 | |
| Class-conditional Image Generation | ImageNet 256x256 (test) | FID3.45 | 167 | |
| Image Generation | ImageNet 256x256 (train) | FID3.45 | 91 | |
| Class-conditional Image Generation | ImageNet-1k (val) | FID3.45 | 68 | |
| Class-conditional generation | ImageNet 256 x 256 1k (val) | FID3.45 | 67 | |
| Class-conditional image synthesis | ImageNet 256x256 (val) | FID3.45 | 61 |