{"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/latent-consistency-models-synthesizing-high","title":"Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference","arxiv_id":"2310.04378","date":"2023-10-06","proceeding":null,"authors":["Simian Luo","Yiqin Tan","Longbo Huang","Jian Li","Hang Zhao"],"abstract":"Latent Diffusion models (LDMs) have achieved remarkable results in synthesizing high-resolution images. However, the iterative sampling process is computationally intensive and leads to slow generation. Inspired by Consistency Models (song et al.), we propose Latent Consistency Models (LCMs), enabling swift inference with minimal steps on any pre-trained LDMs, including Stable Diffusion (rombach et al). Viewing the guided reverse diffusion process as solving an augmented probability flow ODE (PF-ODE), LCMs are designed to directly predict the solution of such ODE in latent space, mitigating the need for numerous iterations and allowing rapid, high-fidelity sampling. Efficiently distilled from pre-trained classifier-free guided diffusion models, a high-quality 768 x 768 2~4-step LCM takes only 32 A100 GPU hours for training. Furthermore, we introduce Latent Consistency Fine-tuning (LCF), a novel method that is tailored for fine-tuning LCMs on customized image datasets. Evaluation on the LAION-5B-Aesthetics dataset demonstrates that LCMs achieve state-of-the-art text-to-image generation performance with few-step inference. Project Page: https://latent-consistency-models.github.io/","url_abs":"https://arxiv.org/abs/2310.04378v1","url_pdf":"https://arxiv.org/pdf/2310.04378v1.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":"latent-consistency-models-synthesizing-high","repo_url":"https://github.com/luosiallen/latent-consistency-model","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"latent-consistency-models-synthesizing-high","repo_url":"https://github.com/Owen-Oertell/rlcm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"latent-consistency-models-synthesizing-high","repo_url":"https://github.com/TFNTF/PostEdit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"latent-consistency-models-synthesizing-high","repo_url":"https://github.com/benearnthof/fm_boosting","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"latent-consistency-models-synthesizing-high","repo_url":"https://github.com/compvis/fm-boosting","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"text-to-image-generation-1","task_name":"Text to Image Generation"},{"task_slug":"text-to-image-generation","task_name":"Text-to-Image Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/text-to-image-generation-on-drawbench","task":"Text-to-Image Generation","dataset":"DrawBench","model":"LCM","rank_in_archive_order":4,"of":8,"metrics":{"Aesthetics (Laion Aesthtetics Predictor)":"5.8038","Human Preference Alignement (HPSv2)":"0.2610","Text Alignement (SentenceBERT)":"0.5602"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2310.04378","atlas_url":"https://app.syntology.ai/?focus=2310.04378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04378"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Owen-Oertell/rlcm","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/benearnthof/fm_boosting","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/compvis/fm-boosting","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/luosiallen/latent-consistency-model","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/TFNTF/PostEdit","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":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":"d81c3ca69afe5db9","entry":"filter_keys","repo":"luosiallen/latent-consistency-model","repo_kind":"official","path":"LCM_Training_Script/consistency_distillation/train_lcm_distill_lora_sd_wds.py","file_url":"https://github.com/luosiallen/latent-consistency-model/blob/HEAD/LCM_Training_Script/consistency_distillation/train_lcm_distill_lora_sd_wds.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d81c3ca69afe5db9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}