{"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/consistency-diffusion-bridge-models","title":"Consistency Diffusion Bridge Models","arxiv_id":"2410.22637","date":"2024-10-30","proceeding":null,"authors":["Guande He","Kaiwen Zheng","Jianfei Chen","Fan Bao","Jun Zhu"],"abstract":"Diffusion models (DMs) have become the dominant paradigm of generative modeling in a variety of domains by learning stochastic processes from noise to data. Recently, diffusion denoising bridge models (DDBMs), a new formulation of generative modeling that builds stochastic processes between fixed data endpoints based on a reference diffusion process, have achieved empirical success across tasks with coupled data distribution, such as image-to-image translation. However, DDBM's sampling process typically requires hundreds of network evaluations to achieve decent performance, which may impede their practical deployment due to high computational demands. In this work, inspired by the recent advance of consistency models in DMs, we tackle this problem by learning the consistency function of the probability-flow ordinary differential equation (PF-ODE) of DDBMs, which directly predicts the solution at a starting step given any point on the ODE trajectory. Based on a dedicated general-form ODE solver, we propose two paradigms: consistency bridge distillation and consistency bridge training, which is flexible to apply on DDBMs with broad design choices. Experimental results show that our proposed method could sample $4\\times$ to $50\\times$ faster than the base DDBM and produce better visual quality given the same step in various tasks with pixel resolution ranging from $64 \\times 64$ to $256 \\times 256$, as well as supporting downstream tasks such as semantic interpolation in the data space.","url_abs":"https://arxiv.org/abs/2410.22637v2","url_pdf":"https://arxiv.org/pdf/2410.22637v2.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":"consistency-diffusion-bridge-models","repo_url":"https://github.com/thu-ml/dbim","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"consistency-diffusion-bridge-models","repo_url":"https://github.com/thu-ml/diffusionbridge","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-to-image-translation","task_name":"Image-to-Image Translation"}],"methods":[{"method_slug":"base","method_name":"BASE"},{"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=2410.22637","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.22637"}},"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/thu-ml/diffusionbridge","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thu-ml/dbim","reach":{"status":"ok"}}],"summary":{"ran_fixture":1,"ran":1,"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"listed":{"samples":4,"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":5,"samples":[{"code_sha256_prefix":"30befb7e4327e615","entry":"append_dims","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"30befb7e4327e615"}},{"code_sha256_prefix":"340bc02a92efdd52","entry":"I2SBNoiseSchedule","repo":"thu-ml/diffusionbridge","repo_kind":"listed","path":"ddbm/karras_diffusion.py","file_url":"https://github.com/thu-ml/diffusionbridge/blob/HEAD/ddbm/karras_diffusion.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":"340bc02a92efdd52"}},{"code_sha256_prefix":"39400baa653fddc7","entry":"ddbm_simulate","repo":"thu-ml/diffusionbridge","repo_kind":"listed","path":"ddbm/karras_diffusion.py","file_url":"https://github.com/thu-ml/diffusionbridge/blob/HEAD/ddbm/karras_diffusion.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"39400baa653fddc7"}},{"code_sha256_prefix":"9ceba2aba6c42ff0","entry":"get_d","repo":"thu-ml/diffusionbridge","repo_kind":"listed","path":"ddbm/karras_diffusion.py","file_url":"https://github.com/thu-ml/diffusionbridge/blob/HEAD/ddbm/karras_diffusion.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9ceba2aba6c42ff0"}},{"code_sha256_prefix":"0db632535ff524e9","entry":"NoiseSchedule","repo":"thu-ml/diffusionbridge","repo_kind":"listed","path":"ddbm/karras_diffusion.py","file_url":"https://github.com/thu-ml/diffusionbridge/blob/HEAD/ddbm/karras_diffusion.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0db632535ff524e9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}