Diffusion Transformer (DiT)
A Diffusion Transformer (DiT) is a transformer-based neural network backbone for diffusion models that replaces the U-Net with a Vision Transformer operating on patches of an image latent.
Explore Image Generation through related topics and the articles other pages reference most.
Articles that also belong to these categories. Counts cover all of Image Generation.
Showing 1-1 of 1 article
A Diffusion Transformer (DiT) is a transformer-based neural network backbone for diffusion models that replaces the U-Net with a Vision Transformer operating on patches of an image latent.