About this paper
A method that removes the decoder from latent diffusion models by adding a final-step prediction head to a finetuned diffusion transformer, reducing inference cost and improving pixel quality in image and video generation.
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…
latent diffusion modelsdecoderdenoised latentsdiffusion transformerlinear headdenoising headDWD headpretrained latent modelsfinetuningtransformer blocks
- Upvotes
- 4
- Authors
- 7
- Published
- Nov 17, 2026
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
Trending history
Decoding Without a Decoder: Direct Pixel Prediction from Diffusion Transformers was first seen on Hugging Face · Daily papers on Nov 19, 2026. Since then it has appeared in 13 checks on 2 different days. Its best position was #10 of 30, reached on Nov 19, 09:29 UTC. It dropped off the list after Nov 20, 03:29 UTC.