{"type":"ScholarlyArticle","title":"GPD: Guided Progressive Distillation for Fast and High-Quality Video Generation","authors":[{"name":"Xiao Liang","slug":"xiao-liang","given":"Xiao","family":"Liang","affiliation":""},{"name":"Yunzhu Zhang","slug":"yunzhu-zhang","given":"Yunzhu","family":"Zhang","affiliation":""},{"name":"Linchao Zhu","slug":"linchao-zhu","given":"Linchao","family":"Zhu","affiliation":""}],"abstract":"Diffusion models have achieved remarkable success in video generation; however, the high computational cost of the denoising process remains a major bottleneck. Existing approaches have shown promise in reducing the number of diffusion steps, but they often suffer from significant quality degradation when applied to video generation. We propose Guided Progressive Distillation (GPD), a framework that accelerates the diffusion process for fast and high-quality video generation.\r\nGPD introduces a novel training strategy in which a teacher model progressively guides a student model to operate with larger step sizes. The framework consists of two key components: (1) an online-generated training target that reduces optimization difficulty while improving computational efficiency, and (2) frequency-domain constraints in the latent space that promote the preservation of fine-grained details and temporal dynamics.\r\nApplied to the Wan2.1 model, GPD reduces the number of sampling steps from 48 to 6 while maintaining competitive visual quality on VBench. Compared with existing distillation methods, GPD demonstrates clear advantages in both pipeline simplicity and quality preservation.","doi":"10.24963/ijcai.2026/157","url":"https://ijcai.org/proceedings/2026/157","pdf":"https://ijcai.org/proceedings/2026/0157.pdf","markdown":"https://ijcai.org/proceedings/2026/157.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/157","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Computer Vision","track":"Main Track","number":157,"pages":{"first":1406,"last":1414},"keywords":["Computer Vision: Image and video synthesis and generation"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}