{"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/migc-multi-instance-generation-controller-for","title":"MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis","arxiv_id":"2402.05408","date":"2024-02-08","proceeding":"CVPR 2024 1","authors":["Dewei Zhou","You Li","Fan Ma","Xiaoting Zhang","Yi Yang"],"abstract":"We present a Multi-Instance Generation (MIG) task, simultaneously generating multiple instances with diverse controls in one image. Given a set of predefined coordinates and their corresponding descriptions, the task is to ensure that generated instances are accurately at the designated locations and that all instances' attributes adhere to their corresponding description. This broadens the scope of current research on Single-instance generation, elevating it to a more versatile and practical dimension. Inspired by the idea of divide and conquer, we introduce an innovative approach named Multi-Instance Generation Controller (MIGC) to address the challenges of the MIG task. Initially, we break down the MIG task into several subtasks, each involving the shading of a single instance. To ensure precise shading for each instance, we introduce an instance enhancement attention mechanism. Lastly, we aggregate all the shaded instances to provide the necessary information for accurately generating multiple instances in stable diffusion (SD). To evaluate how well generation models perform on the MIG task, we provide a COCO-MIG benchmark along with an evaluation pipeline. Extensive experiments were conducted on the proposed COCO-MIG benchmark, as well as on various commonly used benchmarks. The evaluation results illustrate the exceptional control capabilities of our model in terms of quantity, position, attribute, and interaction. Code and demos will be released at https://migcproject.github.io/.","url_abs":"https://arxiv.org/abs/2402.05408v2","url_pdf":"https://arxiv.org/pdf/2402.05408v2.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":"migc-multi-instance-generation-controller-for","repo_url":"https://github.com/limuloo/migc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"conditional-text-to-image-synthesis","task_name":"Conditional Text-to-Image Synthesis"},{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[{"slug":"coco-mig","name":"COCO-MIG","full_name":"COCO-MIG benchmark"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/conditional-text-to-image-synthesis-on-coco-1","task":"Conditional Text-to-Image Synthesis","dataset":"COCO-MIG","model":"MIGC","rank_in_archive_order":1,"of":5,"metrics":{"instance success rate":"0.66","mIoU":"0.56"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.05408","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05408"}},"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/limuloo/migc","reach":null}],"summary":{"ran":7,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":8,"ran":7,"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":9,"samples":[{"code_sha256_prefix":"7e1368435195acfc","entry":"CBAM","repo":"limuloo/migc","repo_kind":"official","path":"migc/migc_arch.py","file_url":"https://github.com/limuloo/migc/blob/HEAD/migc/migc_arch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"7e1368435195acfc"}},{"code_sha256_prefix":"41c4729230248845","entry":"ChannelGate","repo":"limuloo/migc","repo_kind":"official","path":"migc/migc_arch.py","file_url":"https://github.com/limuloo/migc/blob/HEAD/migc/migc_arch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"41c4729230248845"}},{"code_sha256_prefix":"c14fdb4777f76063","entry":"CrossAttention","repo":"limuloo/migc","repo_kind":"official","path":"migc/migc_arch.py","file_url":"https://github.com/limuloo/migc/blob/HEAD/migc/migc_arch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"c14fdb4777f76063"}},{"code_sha256_prefix":"cf57795be166055f","entry":"LayoutAttention","repo":"limuloo/migc","repo_kind":"official","path":"migc/migc_arch.py","file_url":"https://github.com/limuloo/migc/blob/HEAD/migc/migc_arch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"cf57795be166055f"}},{"code_sha256_prefix":"3545cb044aae219f","entry":"PositionNet","repo":"limuloo/migc","repo_kind":"official","path":"migc/migc_arch.py","file_url":"https://github.com/limuloo/migc/blob/HEAD/migc/migc_arch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"3545cb044aae219f"}},{"code_sha256_prefix":"b94c1c2a13728953","entry":"SAC","repo":"limuloo/migc","repo_kind":"official","path":"migc/migc_arch.py","file_url":"https://github.com/limuloo/migc/blob/HEAD/migc/migc_arch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"b94c1c2a13728953"}},{"code_sha256_prefix":"dfdca8dedf1fb371","entry":"SpatialGate","repo":"limuloo/migc","repo_kind":"official","path":"migc/migc_arch.py","file_url":"https://github.com/limuloo/migc/blob/HEAD/migc/migc_arch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"dfdca8dedf1fb371"}},{"code_sha256_prefix":"7abfa32a2f1d7424","entry":"logsumexp_2d","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"7abfa32a2f1d7424"}},{"code_sha256_prefix":"32bdc62bc54343cd","entry":"MIGC","repo":"limuloo/migc","repo_kind":"official","path":"migc/migc_arch.py","file_url":"https://github.com/limuloo/migc/blob/HEAD/migc/migc_arch.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"32bdc62bc54343cd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}