{"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/instancegen-image-generation-with-instance","title":"InstanceGen: Image Generation with Instance-level Instructions","arxiv_id":"2505.05678","date":"2025-05-08","proceeding":null,"authors":["Etai Sella","Yanir Kleiman","Hadar Averbuch-Elor"],"abstract":"Despite rapid advancements in the capabilities of generative models, pretrained text-to-image models still struggle in capturing the semantics conveyed by complex prompts that compound multiple objects and instance-level attributes. Consequently, we are witnessing growing interests in integrating additional structural constraints, typically in the form of coarse bounding boxes, to better guide the generation process in such challenging cases. In this work, we take the idea of structural guidance a step further by making the observation that contemporary image generation models can directly provide a plausible fine-grained structural initialization. We propose a technique that couples this image-based structural guidance with LLM-based instance-level instructions, yielding output images that adhere to all parts of the text prompt, including object counts, instance-level attributes, and spatial relations between instances.","url_abs":"https://arxiv.org/abs/2505.05678v3","url_pdf":"https://arxiv.org/pdf/2505.05678v3.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":"instancegen-image-generation-with-instance","repo_url":"https://github.com/tsunghan-wu/SLD","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.05678","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.05678"}},"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/tsunghan-wu/SLD","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":7},"by_repo_kind":{"official":{"samples":8,"ran":1,"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":"2f1664cb838533c9","entry":"process_input_embeddings","repo":"tsunghan-wu/SLD","repo_kind":"official","path":"models/models.py","file_url":"https://github.com/tsunghan-wu/SLD/blob/HEAD/models/models.py","link_basis":"harvester_set","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":"2f1664cb838533c9"}},{"code_sha256_prefix":"84fea2eda72c2b31","entry":"check_same_object","repo":"tsunghan-wu/SLD","repo_kind":"official","path":"sld/detector.py","file_url":"https://github.com/tsunghan-wu/SLD/blob/HEAD/sld/detector.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":"84fea2eda72c2b31"}},{"code_sha256_prefix":"91d7a81383cf3ed3","entry":"convert_box","repo":"tsunghan-wu/SLD","repo_kind":"official","path":"sld/image_generator.py","file_url":"https://github.com/tsunghan-wu/SLD/blob/HEAD/sld/image_generator.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":"91d7a81383cf3ed3"}},{"code_sha256_prefix":"d362597d148ddba7","entry":"get_key_objects","repo":"tsunghan-wu/SLD","repo_kind":"official","path":"sld/llm_chat.py","file_url":"https://github.com/tsunghan-wu/SLD/blob/HEAD/sld/llm_chat.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":"d362597d148ddba7"}},{"code_sha256_prefix":"ba998aaa812d32a0","entry":"get_updated_layout","repo":"tsunghan-wu/SLD","repo_kind":"official","path":"sld/llm_chat.py","file_url":"https://github.com/tsunghan-wu/SLD/blob/HEAD/sld/llm_chat.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":"ba998aaa812d32a0"}},{"code_sha256_prefix":"fa504d3999b40860","entry":"pop_entry_via_box","repo":"tsunghan-wu/SLD","repo_kind":"official","path":"sld/detector.py","file_url":"https://github.com/tsunghan-wu/SLD/blob/HEAD/sld/detector.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":"fa504d3999b40860"}},{"code_sha256_prefix":"2eff55cf5ebd8ff3","entry":"pop_entry_via_name","repo":"tsunghan-wu/SLD","repo_kind":"official","path":"sld/detector.py","file_url":"https://github.com/tsunghan-wu/SLD/blob/HEAD/sld/detector.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":"2eff55cf5ebd8ff3"}},{"code_sha256_prefix":"5a6df84d20852c60","entry":"run_sam_postprocess","repo":"tsunghan-wu/SLD","repo_kind":"official","path":"sld/utils.py","file_url":"https://github.com/tsunghan-wu/SLD/blob/HEAD/sld/utils.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":"5a6df84d20852c60"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}