Home / AI Research / Decoding Without a Decoder: Direct Pixel Prediction from Diffusion Transformers
DEAI Research
Decoding Without a Decoder: Direct Pixel Prediction from Diffusion Transformers
by StanfordUniversity · Hansheng Chen, Shengqu Cai, Jan Ackermann, Rayhan Zirvi, Gordon Wetzstein, Xinchen Yan
Latent diffusion models rely on a decoder to map denoised latents to pixels, adding complexity and inference cost. We introduce Decoding Without a Decoder (DWD), which lets a finetuned diffusion transformer produce final pixels directly through a linear head. Unlike previous methods, where the denoising output leads to final pixels, DWD separates the two roles: the original denoising head continues to drive sampling, then the new DWD head predicts the pixels at the final step. We extend pretrained latent models with DWD efficiently by finetuning only the last few transformer blocks, training the DWD head with pixel quality losses while anchoring the denoising head to the pretrained model…
Upvotes14
Comments2
Published16 Nov 2026