{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/phased-consistency-model","title":"Phased Consistency Models","arxiv_id":"2405.18407","date":"2024-05-28","proceeding":null,"authors":["Fu-Yun Wang","Zhaoyang Huang","Alexander William Bergman","Dazhong Shen","Peng Gao","Michael Lingelbach","Keqiang Sun","Weikang Bian","Guanglu Song","Yu Liu","Xiaogang Wang","Hongsheng Li"],"abstract":"Consistency Models (CMs) have made significant progress in accelerating the generation of diffusion models. However, their application to high-resolution, text-conditioned image generation in the latent space remains unsatisfactory. In this paper, we identify three key flaws in the current design of Latent Consistency Models (LCMs). We investigate the reasons behind these limitations and propose Phased Consistency Models (PCMs), which generalize the design space and address the identified limitations. Our evaluations demonstrate that PCMs outperform LCMs across 1--16 step generation settings. While PCMs are specifically designed for multi-step refinement, they achieve comparable 1-step generation results to previously state-of-the-art specifically designed 1-step methods. Furthermore, we show the methodology of PCMs is versatile and applicable to video generation, enabling us to train the state-of-the-art few-step text-to-video generator. Our code is available at https://github.com/G-U-N/Phased-Consistency-Model.","url_abs":"https://arxiv.org/abs/2405.18407v2","url_pdf":"https://arxiv.org/pdf/2405.18407v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"phased-consistency-model","repo_url":"https://github.com/G-U-N/Phased-Consistency-Model","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[{"method_slug":"cm","method_name":"Consistency Models"},{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.18407","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.18407"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/G-U-N/Phased-Consistency-Model","reach":null}],"summary":{"ran_fixture":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"f1b675952d115b7f","entry":"guidance_scale_embedding","repo":"G-U-N/Phased-Consistency-Model","repo_kind":"official","path":"code/text_to_image_sd15/train_pcm_lora_sd15.py","file_url":"https://github.com/G-U-N/Phased-Consistency-Model/blob/HEAD/code/text_to_image_sd15/train_pcm_lora_sd15.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f1b675952d115b7f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}