{"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/any-to-any-generation-via-composable","title":"Any-to-Any Generation via Composable Diffusion","arxiv_id":"2305.11846","date":"2023-05-19","proceeding":"NeurIPS 2023 11","authors":["Zineng Tang","ZiYi Yang","Chenguang Zhu","Michael Zeng","Mohit Bansal"],"abstract":"We present Composable Diffusion (CoDi), a novel generative model capable of generating any combination of output modalities, such as language, image, video, or audio, from any combination of input modalities. Unlike existing generative AI systems, CoDi can generate multiple modalities in parallel and its input is not limited to a subset of modalities like text or image. Despite the absence of training datasets for many combinations of modalities, we propose to align modalities in both the input and output space. This allows CoDi to freely condition on any input combination and generate any group of modalities, even if they are not present in the training data. CoDi employs a novel composable generation strategy which involves building a shared multimodal space by bridging alignment in the diffusion process, enabling the synchronized generation of intertwined modalities, such as temporally aligned video and audio. Highly customizable and flexible, CoDi achieves strong joint-modality generation quality, and outperforms or is on par with the unimodal state-of-the-art for single-modality synthesis. The project page with demonstrations and code is at https://codi-gen.github.io","url_abs":"https://arxiv.org/abs/2305.11846v1","url_pdf":"https://arxiv.org/pdf/2305.11846v1.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":"any-to-any-generation-via-composable","repo_url":"https://github.com/microsoft/i-Code/tree/main/i-Code-V3","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"any-to-any-generation-via-composable","repo_url":"https://github.com/see2sound/see2sound","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null}],"tasks":[{"task_slug":"audio-generation","task_name":"Audio Generation"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/audio-generation-on-audiocaps","task":"Audio Generation","dataset":"AudioCaps","model":"CoDi","rank_in_archive_order":18,"of":23,"metrics":{"FAD":"1.80","FD":"22.90"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.11846","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11846"}},"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/see2sound/see2sound","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/microsoft/i-Code/tree/main/i-Code-V3","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"ran_draft_wrong":1,"unverified":11},"by_repo_kind":{"official":{"samples":13,"ran":2,"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":"9f1130d32c6430f8","entry":"get_last_checkpoint","repo":"microsoft/i-Code","repo_kind":"official","path":"i-Code-Doc/core/common/utils.py","file_url":"https://github.com/microsoft/i-Code/blob/HEAD/i-Code-Doc/core/common/utils.py","link_basis":"plan_row","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":"9f1130d32c6430f8"}},{"code_sha256_prefix":"a57e939b71fd9a3d","entry":"singleton","repo":"microsoft/i-Code","repo_kind":"official","path":"i-Code-V3/core/cfg_holder.py","file_url":"https://github.com/microsoft/i-Code/blob/HEAD/i-Code-V3/core/cfg_holder.py","link_basis":"harvester_set","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":"a57e939b71fd9a3d"}},{"code_sha256_prefix":"c30c690fa7c2a6bb","entry":"cfg_solve","repo":"microsoft/i-Code","repo_kind":"official","path":"i-Code-V3/core/cfg_helper.py","file_url":"https://github.com/microsoft/i-Code/blob/HEAD/i-Code-V3/core/cfg_helper.py","link_basis":"first_harvest_node","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":"c30c690fa7c2a6bb"}},{"code_sha256_prefix":"9db485e862ec2a41","entry":"cfg_solvef","repo":"microsoft/i-Code","repo_kind":"official","path":"i-Code-V3/core/cfg_helper.py","file_url":"https://github.com/microsoft/i-Code/blob/HEAD/i-Code-V3/core/cfg_helper.py","link_basis":"first_harvest_node","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":"9db485e862ec2a41"}},{"code_sha256_prefix":"59eacee354fa7772","entry":"clamp","repo":"microsoft/i-Code","repo_kind":"official","path":"i-Code-Doc/core/common/utils.py","file_url":"https://github.com/microsoft/i-Code/blob/HEAD/i-Code-Doc/core/common/utils.py","link_basis":"first_harvest_node","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":"59eacee354fa7772"}},{"code_sha256_prefix":"e41a75c06c761585","entry":"get_bb","repo":"microsoft/i-Code","repo_kind":"official","path":"i-Code-Doc/core/datasets/rvlcdip.py","file_url":"https://github.com/microsoft/i-Code/blob/HEAD/i-Code-Doc/core/datasets/rvlcdip.py","link_basis":"first_harvest_node","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":"e41a75c06c761585"}},{"code_sha256_prefix":"d1949a1bc1a12110","entry":"get_prop","repo":"microsoft/i-Code","repo_kind":"official","path":"i-Code-Doc/core/datasets/rvlcdip.py","file_url":"https://github.com/microsoft/i-Code/blob/HEAD/i-Code-Doc/core/datasets/rvlcdip.py","link_basis":"first_harvest_node","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":"d1949a1bc1a12110"}},{"code_sha256_prefix":"5804369ab36a8596","entry":"get_rank","repo":"microsoft/i-Code","repo_kind":"official","path":"i-Code-V3/core/sync.py","file_url":"https://github.com/microsoft/i-Code/blob/HEAD/i-Code-V3/core/sync.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":"5804369ab36a8596"}},{"code_sha256_prefix":"9108f4e8ddaf0e74","entry":"get_visual_bbox","repo":"microsoft/i-Code","repo_kind":"official","path":"i-Code-Doc/core/common/utils.py","file_url":"https://github.com/microsoft/i-Code/blob/HEAD/i-Code-Doc/core/common/utils.py","link_basis":"first_harvest_node","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":"9108f4e8ddaf0e74"}},{"code_sha256_prefix":"bc7bb42126c207b8","entry":"get_world_size","repo":"microsoft/i-Code","repo_kind":"official","path":"i-Code-V3/core/sync.py","file_url":"https://github.com/microsoft/i-Code/blob/HEAD/i-Code-V3/core/sync.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":"bc7bb42126c207b8"}},{"code_sha256_prefix":"8ee1c82c537f8cdb","entry":"load_cfg_yaml","repo":"microsoft/i-Code","repo_kind":"official","path":"i-Code-V3/core/cfg_helper.py","file_url":"https://github.com/microsoft/i-Code/blob/HEAD/i-Code-V3/core/cfg_helper.py","link_basis":"first_harvest_node","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":"8ee1c82c537f8cdb"}},{"code_sha256_prefix":"b2ec63c33e2f1695","entry":"normalText","repo":"microsoft/i-Code","repo_kind":"official","path":"i-Code-Doc/core/datasets/rvlcdip.py","file_url":"https://github.com/microsoft/i-Code/blob/HEAD/i-Code-Doc/core/datasets/rvlcdip.py","link_basis":"first_harvest_node","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":"b2ec63c33e2f1695"}},{"code_sha256_prefix":"f22f1431ae37e29b","entry":"setup_registry","repo":"microsoft/i-Code","repo_kind":"official","path":"i-Code-Doc/core/common/registry.py","file_url":"https://github.com/microsoft/i-Code/blob/HEAD/i-Code-Doc/core/common/registry.py","link_basis":"first_harvest_node","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":"f22f1431ae37e29b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}