{"ID":2889141,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.21690","arxiv_id":"2507.21690","title":"APT: Improving Diffusion Models for High Resolution Image Generation with Adaptive Path Tracing","abstract":"Latent Diffusion Models (LDMs) are generally trained at fixed resolutions, limiting their capability when scaling up to high-resolution images. While training-based approaches address this limitation by training on high-resolution datasets, they require large amounts of data and considerable computational resources, making them less practical. Consequently, training-free methods, particularly patch-based approaches, have become a popular alternative. These methods divide an image into patches and fuse the denoising paths of each patch, showing strong performance on high-resolution generation. However, we observe two critical issues for patch-based approaches, which we call ``patch-level distribution shift\" and ``increased patch monotonicity.\" To address these issues, we propose Adaptive Path Tracing (APT), a framework that combines Statistical Matching to ensure patch distributions remain consistent in upsampled latents and Scale-aware Scheduling to deal with the patch monotonicity. As a result, APT produces clearer and more refined details in high-resolution images. In addition, APT enables a shortcut denoising process, resulting in faster sampling with minimal quality degradation. Our experimental results confirm that APT produces more detailed outputs with improved inference speed, providing a practical approach to high-resolution image generation.","short_abstract":"Latent Diffusion Models (LDMs) are generally trained at fixed resolutions, limiting their capability when scaling up to high-resolution images. While training-based approaches address this limitation by training on high-resolution datasets, they require large amounts of data and considerable computational resources, ma...","url_abs":"https://arxiv.org/abs/2507.21690","url_pdf":"https://arxiv.org/pdf/2507.21690v1","authors":"[\"Sangmin Han\",\"Jinho Jeong\",\"Jinwoo Kim\",\"Seon Joo Kim\"]","published":"2025-07-29T11:13:03Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[\"Diffusion Model\"]","has_code":false}