Hugging Face Papers ↗ · 2026-11-17
Decoding Without a Decoder: Direct Pixel Prediction from Diffusion Transformers
Media reports Hugging Face Papers Source language: Chinese
Latent diffusion models rely on a decoder to map denoised latents to pixels, adding complexity and inference cost.
Full text
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.