{"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/hico-hierarchical-controllable-diffusion","title":"HiCo: Hierarchical Controllable Diffusion Model for Layout-to-image Generation","arxiv_id":"2410.14324","date":"2024-10-18","proceeding":null,"authors":["Bo Cheng","Yuhang Ma","Liebucha Wu","Shanyuan Liu","Ao Ma","Xiaoyu Wu","Dawei Leng","Yuhui Yin"],"abstract":"The task of layout-to-image generation involves synthesizing images based on the captions of objects and their spatial positions. Existing methods still struggle in complex layout generation, where common bad cases include object missing, inconsistent lighting, conflicting view angles, etc. To effectively address these issues, we propose a \\textbf{Hi}erarchical \\textbf{Co}ntrollable (HiCo) diffusion model for layout-to-image generation, featuring object seperable conditioning branch structure. Our key insight is to achieve spatial disentanglement through hierarchical modeling of layouts. We use a multi branch structure to represent hierarchy and aggregate them in fusion module. To evaluate the performance of multi-objective controllable layout generation in natural scenes, we introduce the HiCo-7K benchmark, derived from the GRIT-20M dataset and manually cleaned. https://github.com/360CVGroup/HiCo_T2I.","url_abs":"https://arxiv.org/abs/2410.14324v1","url_pdf":"https://arxiv.org/pdf/2410.14324v1.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":"hico-hierarchical-controllable-diffusion","repo_url":"https://github.com/360cvgroup/hico_t2i","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok"}}],"tasks":[{"task_slug":"disentanglement","task_name":"Disentanglement"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"layout-generation","task_name":"Layout Generation"},{"task_slug":"layout-to-image-generation","task_name":"Layout-to-Image Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.14324","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14324"}},"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/360cvgroup/hico_t2i","reach":{"status":"ok"}}],"summary":{"ran":10,"ran_draft_wrong":2,"ran_fixture":1},"by_repo_kind":{"official":{"samples":13,"ran":13,"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":13,"samples":[{"code_sha256_prefix":"b73019e015025aca","entry":"blank","repo":"360cvgroup/hico_t2i","repo_kind":"official","path":"dataset/util.py","file_url":"https://github.com/360cvgroup/hico_t2i/blob/HEAD/dataset/util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b73019e015025aca"}},{"code_sha256_prefix":"8a46d8eebdd6d3e5","entry":"coco_collate_fn_for_layout","repo":"360cvgroup/hico_t2i","repo_kind":"official","path":"dataset/coco.py","file_url":"https://github.com/360cvgroup/hico_t2i/blob/HEAD/dataset/coco.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":"8a46d8eebdd6d3e5"}},{"code_sha256_prefix":"b7180286487d1d3e","entry":"get_maximum_bbox","repo":"360cvgroup/hico_t2i","repo_kind":"official","path":"eval/cal_ap_step1.py","file_url":"https://github.com/360cvgroup/hico_t2i/blob/HEAD/eval/cal_ap_step1.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":"b7180286487d1d3e"}},{"code_sha256_prefix":"221b2d116fdf1032","entry":"get_obj_from_str","repo":"360cvgroup/hico_t2i","repo_kind":"official","path":"train_hico.py","file_url":"https://github.com/360cvgroup/hico_t2i/blob/HEAD/train_hico.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"221b2d116fdf1032"}},{"code_sha256_prefix":"ea78ccce462a225c","entry":"grit_collate_fn_for_layout","repo":"360cvgroup/hico_t2i","repo_kind":"official","path":"dataset/grit.py","file_url":"https://github.com/360cvgroup/hico_t2i/blob/HEAD/dataset/grit.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":"ea78ccce462a225c"}},{"code_sha256_prefix":"bd5a05ce886da4ce","entry":"image_grid","repo":"360cvgroup/hico_t2i","repo_kind":"official","path":"train_hico.py","file_url":"https://github.com/360cvgroup/hico_t2i/blob/HEAD/train_hico.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bd5a05ce886da4ce"}},{"code_sha256_prefix":"e3a1bf4f39265059","entry":"image_unnormalize","repo":"360cvgroup/hico_t2i","repo_kind":"official","path":"dataset/util.py","file_url":"https://github.com/360cvgroup/hico_t2i/blob/HEAD/dataset/util.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":"e3a1bf4f39265059"}},{"code_sha256_prefix":"6ec11ee890696819","entry":"intersect","repo":"360cvgroup/hico_t2i","repo_kind":"official","path":"dataset/augmentations.py","file_url":"https://github.com/360cvgroup/hico_t2i/blob/HEAD/dataset/augmentations.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6ec11ee890696819"}},{"code_sha256_prefix":"13675bf1f3f88001","entry":"jaccard_numpy","repo":"360cvgroup/hico_t2i","repo_kind":"official","path":"dataset/augmentations.py","file_url":"https://github.com/360cvgroup/hico_t2i/blob/HEAD/dataset/augmentations.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"13675bf1f3f88001"}},{"code_sha256_prefix":"f81993bbb1d7686b","entry":"load_image","repo":"360cvgroup/hico_t2i","repo_kind":"official","path":"infer-avg.py","file_url":"https://github.com/360cvgroup/hico_t2i/blob/HEAD/infer-avg.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":"f81993bbb1d7686b"}},{"code_sha256_prefix":"902c5d0108a6663c","entry":"rescale","repo":"360cvgroup/hico_t2i","repo_kind":"official","path":"dataset/util.py","file_url":"https://github.com/360cvgroup/hico_t2i/blob/HEAD/dataset/util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"902c5d0108a6663c"}},{"code_sha256_prefix":"bea2d776a332f2b0","entry":"rescale_noise_cfg","repo":"360cvgroup/hico_t2i","repo_kind":"official","path":"diffusers/src/diffusers/pipelines/t2i_adapter/pipeline_stable_diffusion_xl_adapter.py","file_url":"https://github.com/360cvgroup/hico_t2i/blob/HEAD/diffusers/src/diffusers/pipelines/t2i_adapter/pipeline_stable_diffusion_xl_adapter.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bea2d776a332f2b0"}},{"code_sha256_prefix":"d315cf9de0fe3526","entry":"voc_ap","repo":"360cvgroup/hico_t2i","repo_kind":"official","path":"eval/cal_ap_step2.py","file_url":"https://github.com/360cvgroup/hico_t2i/blob/HEAD/eval/cal_ap_step2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d315cf9de0fe3526"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}