PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion

by [unverified] · free · Last verified 2026-06-21T03:07:53.000Z

Most practical high-resolution text-to-image systems, including latent diffusion and autoregressive models, perform generation in a compact latent space, and a decoder maps the generated latents back to pixels. Yet the latent-to-pixel decoder is reconstruction-oriented, optimized to invert the en...