{"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/layoutdiffusion-controllable-diffusion-model","title":"LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation","arxiv_id":"2303.17189","date":"2023-03-30","proceeding":"CVPR 2023 1","authors":["Guangcong Zheng","Xianpan Zhou","XueWei Li","Zhongang Qi","Ying Shan","Xi Li"],"abstract":"Recently, diffusion models have achieved great success in image synthesis. However, when it comes to the layout-to-image generation where an image often has a complex scene of multiple objects, how to make strong control over both the global layout map and each detailed object remains a challenging task. In this paper, we propose a diffusion model named LayoutDiffusion that can obtain higher generation quality and greater controllability than the previous works. To overcome the difficult multimodal fusion of image and layout, we propose to construct a structural image patch with region information and transform the patched image into a special layout to fuse with the normal layout in a unified form. Moreover, Layout Fusion Module (LFM) and Object-aware Cross Attention (OaCA) are proposed to model the relationship among multiple objects and designed to be object-aware and position-sensitive, allowing for precisely controlling the spatial related information. Extensive experiments show that our LayoutDiffusion outperforms the previous SOTA methods on FID, CAS by relatively 46.35%, 26.70% on COCO-stuff and 44.29%, 41.82% on VG. Code is available at https://github.com/ZGCTroy/LayoutDiffusion.","url_abs":"https://arxiv.org/abs/2303.17189v2","url_pdf":"https://arxiv.org/pdf/2303.17189v2.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":"layoutdiffusion-controllable-diffusion-model","repo_url":"https://github.com/dcdcvgroup/layout-diffusion-mindspore","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"layoutdiffusion-controllable-diffusion-model","repo_url":"https://github.com/zgctroy/layoutdiffusion","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"layout-to-image-generation","task_name":"Layout-to-Image Generation"},{"task_slug":"object","task_name":"Object"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/layout-to-image-generation-on-coco-stuff-4","task":"Layout-to-Image Generation","dataset":"COCO-Stuff 256x256","model":"LayoutDiffusion (25steps)","rank_in_archive_order":1,"of":5,"metrics":{"FID":"31.68"},"uses_additional_data":false},{"leaderboard":"/sota/layout-to-image-generation-on-visual-genome-3","task":"Layout-to-Image Generation","dataset":"Visual Genome 128x128","model":"LayoutDiffusion","rank_in_archive_order":1,"of":5,"metrics":{"FID":"16.35"},"uses_additional_data":false},{"leaderboard":"/sota/layout-to-image-generation-on-visual-genome-4","task":"Layout-to-Image Generation","dataset":"Visual Genome 256x256","model":"LayoutDiffusion","rank_in_archive_order":1,"of":4,"metrics":{"FID":"15.63"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.17189","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.17189"}},"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/dcdcvgroup/layout-diffusion-mindspore","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zgctroy/layoutdiffusion","reach":null}],"summary":{"ran":2,"ran_honours":2,"ran_draft_wrong":1,"unverified":14},"by_repo_kind":{"official":{"samples":12,"ran":3,"repositories":1},"named_in_paper":{"samples":7,"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":"b8ac15fc31c4c31d","entry":"QKVAttentionLegacy","repo":"zgctroy/layoutdiffusion","repo_kind":"named_in_paper","path":"layout_diffusion/layout_diffusion_unet.py","file_url":"https://github.com/zgctroy/layoutdiffusion/blob/HEAD/layout_diffusion/layout_diffusion_unet.py","link_basis":"first_harvest_node","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":"b8ac15fc31c4c31d"}},{"code_sha256_prefix":"52fcaa6065df3ee1","entry":"SiLU","repo":"zgctroy/layoutdiffusion","repo_kind":"named_in_paper","path":"layout_diffusion/layout_diffusion_unet.py","file_url":"https://github.com/zgctroy/layoutdiffusion/blob/HEAD/layout_diffusion/layout_diffusion_unet.py","link_basis":"first_harvest_node","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":"52fcaa6065df3ee1"}},{"code_sha256_prefix":"2ab2316ac6fdd869","entry":"betas_for_alpha_bar","repo":"dcdcvgroup/layout-diffusion-mindspore","repo_kind":"official","path":"layout_diffusion/gaussian_diffusion.py","file_url":"https://github.com/dcdcvgroup/layout-diffusion-mindspore/blob/HEAD/layout_diffusion/gaussian_diffusion.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2ab2316ac6fdd869"}},{"code_sha256_prefix":"a086d6286a40b889","entry":"get_named_beta_schedule","repo":"dcdcvgroup/layout-diffusion-mindspore","repo_kind":"official","path":"layout_diffusion/gaussian_diffusion.py","file_url":"https://github.com/dcdcvgroup/layout-diffusion-mindspore/blob/HEAD/layout_diffusion/gaussian_diffusion.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a086d6286a40b889"}},{"code_sha256_prefix":"221b2d116fdf1032","entry":"get_obj_from_str","repo":"dcdcvgroup/layout-diffusion-mindspore","repo_kind":"official","path":"layout_diffusion/util.py","file_url":"https://github.com/dcdcvgroup/layout-diffusion-mindspore/blob/HEAD/layout_diffusion/util.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"221b2d116fdf1032"}},{"code_sha256_prefix":"53b0dd52d7b30b22","entry":"AttentionBlock","repo":"zgctroy/layoutdiffusion","repo_kind":"named_in_paper","path":"layout_diffusion/layout_diffusion_unet.py","file_url":"https://github.com/zgctroy/layoutdiffusion/blob/HEAD/layout_diffusion/layout_diffusion_unet.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":"53b0dd52d7b30b22"}},{"code_sha256_prefix":"c0bc3ed1be627926","entry":"LayoutDiffusionUNetModel","repo":"zgctroy/layoutdiffusion","repo_kind":"named_in_paper","path":"layout_diffusion/layout_diffusion_unet.py","file_url":"https://github.com/zgctroy/layoutdiffusion/blob/HEAD/layout_diffusion/layout_diffusion_unet.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":"c0bc3ed1be627926"}},{"code_sha256_prefix":"1953cbb549533769","entry":"ObjectAwareCrossAttention","repo":"zgctroy/layoutdiffusion","repo_kind":"named_in_paper","path":"layout_diffusion/layout_diffusion_unet.py","file_url":"https://github.com/zgctroy/layoutdiffusion/blob/HEAD/layout_diffusion/layout_diffusion_unet.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":"1953cbb549533769"}},{"code_sha256_prefix":"45cf54c7a28a7147","entry":"ResBlock","repo":"zgctroy/layoutdiffusion","repo_kind":"named_in_paper","path":"layout_diffusion/layout_diffusion_unet.py","file_url":"https://github.com/zgctroy/layoutdiffusion/blob/HEAD/layout_diffusion/layout_diffusion_unet.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":"45cf54c7a28a7147"}},{"code_sha256_prefix":"d174605e83159ebd","entry":"TimestepEmbedSequential","repo":"zgctroy/layoutdiffusion","repo_kind":"named_in_paper","path":"layout_diffusion/layout_diffusion_unet.py","file_url":"https://github.com/zgctroy/layoutdiffusion/blob/HEAD/layout_diffusion/layout_diffusion_unet.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":"d174605e83159ebd"}},{"code_sha256_prefix":"43112d6fc1a61a07","entry":"build_diffusion","repo":"dcdcvgroup/layout-diffusion-mindspore","repo_kind":"official","path":"layout_diffusion/respace.py","file_url":"https://github.com/dcdcvgroup/layout-diffusion-mindspore/blob/HEAD/layout_diffusion/respace.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":"43112d6fc1a61a07"}},{"code_sha256_prefix":"f07113626bc2a9ae","entry":"build_model","repo":"dcdcvgroup/layout-diffusion-mindspore","repo_kind":"official","path":"layout_diffusion/layout_diffusion_unet.py","file_url":"https://github.com/dcdcvgroup/layout-diffusion-mindspore/blob/HEAD/layout_diffusion/layout_diffusion_unet.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":"f07113626bc2a9ae"}},{"code_sha256_prefix":"c9462fd26014eb95","entry":"get_param_groups_and_shapes","repo":"dcdcvgroup/layout-diffusion-mindspore","repo_kind":"official","path":"layout_diffusion/fp16_util.py","file_url":"https://github.com/dcdcvgroup/layout-diffusion-mindspore/blob/HEAD/layout_diffusion/fp16_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":"c9462fd26014eb95"}},{"code_sha256_prefix":"2675c6c9bf8c7023","entry":"make_master_params","repo":"dcdcvgroup/layout-diffusion-mindspore","repo_kind":"official","path":"layout_diffusion/fp16_util.py","file_url":"https://github.com/dcdcvgroup/layout-diffusion-mindspore/blob/HEAD/layout_diffusion/fp16_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":"2675c6c9bf8c7023"}},{"code_sha256_prefix":"f1f1aa73de47c1e0","entry":"make_output_format","repo":"dcdcvgroup/layout-diffusion-mindspore","repo_kind":"official","path":"layout_diffusion/logger.py","file_url":"https://github.com/dcdcvgroup/layout-diffusion-mindspore/blob/HEAD/layout_diffusion/logger.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":"f1f1aa73de47c1e0"}},{"code_sha256_prefix":"e515a67f7f32e76d","entry":"mpi_weighted_mean","repo":"dcdcvgroup/layout-diffusion-mindspore","repo_kind":"official","path":"layout_diffusion/logger.py","file_url":"https://github.com/dcdcvgroup/layout-diffusion-mindspore/blob/HEAD/layout_diffusion/logger.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":"e515a67f7f32e76d"}},{"code_sha256_prefix":"192c365338335653","entry":"parse_resume_step_from_filename","repo":"dcdcvgroup/layout-diffusion-mindspore","repo_kind":"official","path":"layout_diffusion/train_util.py","file_url":"https://github.com/dcdcvgroup/layout-diffusion-mindspore/blob/HEAD/layout_diffusion/train_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":"192c365338335653"}},{"code_sha256_prefix":"37ddaf228c202902","entry":"space_timesteps","repo":"dcdcvgroup/layout-diffusion-mindspore","repo_kind":"official","path":"layout_diffusion/respace.py","file_url":"https://github.com/dcdcvgroup/layout-diffusion-mindspore/blob/HEAD/layout_diffusion/respace.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":"37ddaf228c202902"}},{"code_sha256_prefix":"d36d1fd554cb479f","entry":"unflatten_master_params","repo":"dcdcvgroup/layout-diffusion-mindspore","repo_kind":"official","path":"layout_diffusion/fp16_util.py","file_url":"https://github.com/dcdcvgroup/layout-diffusion-mindspore/blob/HEAD/layout_diffusion/fp16_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":"d36d1fd554cb479f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}