{"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/inconsistencies-in-consistency-models-better","title":"Inconsistencies In Consistency Models: Better ODE Solving Does Not Imply Better Samples","arxiv_id":"2411.08954","date":"2024-11-13","proceeding":null,"authors":["Noël Vouitsis","Rasa Hosseinzadeh","Brendan Leigh Ross","Valentin Villecroze","Satya Krishna Gorti","Jesse C. Cresswell","Gabriel Loaiza-Ganem"],"abstract":"Although diffusion models can generate remarkably high-quality samples, they are intrinsically bottlenecked by their expensive iterative sampling procedure. Consistency models (CMs) have recently emerged as a promising diffusion model distillation method, reducing the cost of sampling by generating high-fidelity samples in just a few iterations. Consistency model distillation aims to solve the probability flow ordinary differential equation (ODE) defined by an existing diffusion model. CMs are not directly trained to minimize error against an ODE solver, rather they use a more computationally tractable objective. As a way to study how effectively CMs solve the probability flow ODE, and the effect that any induced error has on the quality of generated samples, we introduce Direct CMs, which \\textit{directly} minimize this error. Intriguingly, we find that Direct CMs reduce the ODE solving error compared to CMs but also result in significantly worse sample quality, calling into question why exactly CMs work well in the first place. Full code is available at: https://github.com/layer6ai-labs/direct-cms.","url_abs":"https://arxiv.org/abs/2411.08954v2","url_pdf":"https://arxiv.org/pdf/2411.08954v2.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":"inconsistencies-in-consistency-models-better","repo_url":"https://github.com/layer6ai-labs/direct-cms","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"cm","method_name":"Consistency Models"},{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2411.08954","atlas_url":"https://app.syntology.ai/?focus=2411.08954","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.08954"}},"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":"deterministic:regex_extraction","url":"https://github.com/layer6ai-labs/direct-cms","reach":null}],"summary":{"ran_fixture":1,"ran":1,"ran_violates":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"30befb7e4327e615","entry":"append_dims","repo":"layer6ai-labs/direct-cms","repo_kind":"official","path":"train_direct_cm.py","file_url":"https://github.com/layer6ai-labs/direct-cms/blob/HEAD/train_direct_cm.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"30befb7e4327e615"}},{"code_sha256_prefix":"f71a8f9fc50ff34f","entry":"DDIMSolver","repo":"layer6ai-labs/direct-cms","repo_kind":"official","path":"train_direct_cm.py","file_url":"https://github.com/layer6ai-labs/direct-cms/blob/HEAD/train_direct_cm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f71a8f9fc50ff34f"}},{"code_sha256_prefix":"74a9b4e5e34c0860","entry":"scalings_for_boundary_conditions","repo":"layer6ai-labs/direct-cms","repo_kind":"official","path":"train_direct_cm.py","file_url":"https://github.com/layer6ai-labs/direct-cms/blob/HEAD/train_direct_cm.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"74a9b4e5e34c0860"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}