{"ID":2859961,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.04961","arxiv_id":"2510.04961","title":"SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenization","abstract":"Tokenizers are a key component of state-of-the-art generative image models, extracting the most important features from the signal while reducing data dimension and redundancy. Most current tokenizers are based on KL-regularized variational autoencoders (KL-VAE), trained with reconstruction, perceptual and adversarial losses. Diffusion decoders have been proposed as a more principled alternative to model the distribution over images conditioned on the latent. However, matching the performance of KL-VAE still requires adversarial losses, as well as a higher decoding time due to iterative sampling. To address these limitations, we introduce a new pixel diffusion decoder architecture for improved scaling and training stability, benefiting from transformer components and GAN-free training. We use distillation to replicate the performance of the diffusion decoder in an efficient single-step decoder. This makes SSDD the first diffusion decoder optimized for single-step reconstruction trained without adversarial losses, reaching higher reconstruction quality and faster sampling than KL-VAE. In particular, SSDD improves reconstruction FID from $0.87$ to $0.50$ with $1.4\\times$ higher throughput and preserve generation quality of DiTs with $3.8\\times$ faster sampling. As such, SSDD can be used as a drop-in replacement for KL-VAE, and for building higher-quality and faster generative models.","short_abstract":"Tokenizers are a key component of state-of-the-art generative image models, extracting the most important features from the signal while reducing data dimension and redundancy. Most current tokenizers are based on KL-regularized variational autoencoders (KL-VAE), trained with reconstruction, perceptual and adversarial...","url_abs":"https://arxiv.org/abs/2510.04961","url_pdf":"https://arxiv.org/pdf/2510.04961v1","authors":"[\"Théophane Vallaeys\",\"Jakob Verbeek\",\"Matthieu Cord\"]","published":"2025-10-06T15:57:31Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\",\"Transformer\",\"Generative Adversarial Network\",\"Variational Autoencoder\"]","has_code":false}