{"ID":2837370,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.18822","arxiv_id":"2511.18822","title":"DiP: Taming Diffusion Models in Pixel Space","abstract":"Diffusion models face a fundamental trade-off between generation quality and computational efficiency. Latent Diffusion Models (LDMs) offer an efficient solution but suffer from potential information loss and non-end-to-end training. In contrast, existing pixel space models bypass VAEs but are computationally prohibitive for high-resolution synthesis. To resolve this dilemma, we propose DiP, an efficient pixel space diffusion framework. DiP decouples generation into a global and a local stage: a Diffusion Transformer (DiT) backbone operates on large patches for efficient global structure construction, while a co-trained lightweight Patch Detailer Head leverages contextual features to restore fine-grained local details. This synergistic design achieves computational efficiency comparable to LDMs without relying on a VAE. DiP is accomplished with up to 10$\\times$ faster inference speeds than previous method while increasing the total number of parameters by only 0.3%, and achieves an 1.79 FID score on ImageNet 256$\\times$256.","short_abstract":"Diffusion models face a fundamental trade-off between generation quality and computational efficiency. Latent Diffusion Models (LDMs) offer an efficient solution but suffer from potential information loss and non-end-to-end training. In contrast, existing pixel space models bypass VAEs but are computationally prohibiti...","url_abs":"https://arxiv.org/abs/2511.18822","url_pdf":"https://arxiv.org/pdf/2511.18822v3","authors":"[\"Zhennan Chen\",\"Junwei Zhu\",\"Xu Chen\",\"Jiangning Zhang\",\"Xiaobin Hu\",\"Hanzhen Zhao\",\"Chengjie Wang\",\"Jian Yang\",\"Ying Tai\"]","published":"2025-11-24T06:55:49Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\",\"Transformer\",\"Variational Autoencoder\"]","has_code":false}