Diffusion-GAN
UT AustinMicrosoftImage generationText-to-imageOpen weights
Diffusion-GAN is a image generation model from UT Austin,Microsoft released in 2022.
About Diffusion-GAN
Generative adversarial networks (GANs) are challenging to train stably, and a promising remedy of injecting instance noise into the discriminator input has not been very effective in practice. In this paper, we propose Diffusion-GAN, a novel GAN fram
Details
- Provider
- UT Austin,Microsoft
- Task
- Image generation,Text-to-image
- Released
- 2022-06-05
- Open weights
- Yes