{"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/training-consistency-models-with-variational","title":"Training Consistency Models with Variational Noise Coupling","arxiv_id":"2502.18197","date":"2025-02-25","proceeding":null,"authors":["Gianluigi Silvestri","Luca Ambrogioni","Chieh-Hsin Lai","Yuhta Takida","Yuki Mitsufuji"],"abstract":"Consistency Training (CT) has recently emerged as a promising alternative to diffusion models, achieving competitive performance in image generation tasks. However, non-distillation consistency training often suffers from high variance and instability, and analyzing and improving its training dynamics is an active area of research. In this work, we propose a novel CT training approach based on the Flow Matching framework. Our main contribution is a trained noise-coupling scheme inspired by the architecture of Variational Autoencoders (VAE). By training a data-dependent noise emission model implemented as an encoder architecture, our method can indirectly learn the geometry of the noise-to-data mapping, which is instead fixed by the choice of the forward process in classical CT. Empirical results across diverse image datasets show significant generative improvements, with our model outperforming baselines and achieving the state-of-the-art (SoTA) non-distillation CT FID on CIFAR-10, and attaining FID on par with SoTA on ImageNet at $64 \\times 64$ resolution in 2-step generation. Our code is available at https://github.com/sony/vct .","url_abs":"https://arxiv.org/abs/2502.18197v1","url_pdf":"https://arxiv.org/pdf/2502.18197v1.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":"training-consistency-models-with-variational","repo_url":"https://github.com/sony/vct","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2502.18197","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.18197"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sony/vct","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"ran":2,"ran_fixture":1,"unverified":1},"by_repo_kind":{"official":{"samples":6,"ran":5,"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":"674eca7b9e1b6439","entry":"format_time","repo":"sony/vct","repo_kind":"official","path":"dnnlib/util.py","file_url":"https://github.com/sony/vct/blob/HEAD/dnnlib/util.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"674eca7b9e1b6439"}},{"code_sha256_prefix":"32af001972a0699f","entry":"format_time_brief","repo":"sony/vct","repo_kind":"official","path":"dnnlib/util.py","file_url":"https://github.com/sony/vct/blob/HEAD/dnnlib/util.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"32af001972a0699f"}},{"code_sha256_prefix":"49d89884be5dc515","entry":"mp_silu","repo":"sony/vct","repo_kind":"official","path":"networks/networks_edm2.py","file_url":"https://github.com/sony/vct/blob/HEAD/networks/networks_edm2.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"49d89884be5dc515"}},{"code_sha256_prefix":"ebfd171dc25ba0ce","entry":"normalize","repo":"sony/vct","repo_kind":"official","path":"networks/networks_edm2.py","file_url":"https://github.com/sony/vct/blob/HEAD/networks/networks_edm2.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ebfd171dc25ba0ce"}},{"code_sha256_prefix":"d41a4250066bce93","entry":"weight_init","repo":"sony/vct","repo_kind":"official","path":"networks/edm_networks.py","file_url":"https://github.com/sony/vct/blob/HEAD/networks/edm_networks.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d41a4250066bce93"}},{"code_sha256_prefix":"9d31d2c4cd16bb2d","entry":"ask_yes_no","repo":"sony/vct","repo_kind":"official","path":"dnnlib/util.py","file_url":"https://github.com/sony/vct/blob/HEAD/dnnlib/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9d31d2c4cd16bb2d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}