{"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/xverse-consistent-multi-subject-control-of","title":"XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation","arxiv_id":"2506.21416","date":"2025-06-26","proceeding":null,"authors":["Bowen Chen","Mengyi Zhao","Haomiao Sun","Li Chen","Xu Wang","Kang Du","Xinglong Wu"],"abstract":"Achieving fine-grained control over subject identity and semantic attributes (pose, style, lighting) in text-to-image generation, particularly for multiple subjects, often undermines the editability and coherence of Diffusion Transformers (DiTs). Many approaches introduce artifacts or suffer from attribute entanglement. To overcome these challenges, we propose a novel multi-subject controlled generation model XVerse. By transforming reference images into offsets for token-specific text-stream modulation, XVerse allows for precise and independent control for specific subject without disrupting image latents or features. Consequently, XVerse offers high-fidelity, editable multi-subject image synthesis with robust control over individual subject characteristics and semantic attributes. This advancement significantly improves personalized and complex scene generation capabilities.","url_abs":"https://arxiv.org/abs/2506.21416v1","url_pdf":"https://arxiv.org/pdf/2506.21416v1.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":"xverse-consistent-multi-subject-control-of","repo_url":"https://github.com/bytedance/xverse","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"scene-generation","task_name":"Scene Generation"},{"task_slug":"text-to-image-generation-1","task_name":"Text to Image Generation"},{"task_slug":"text-to-image-generation","task_name":"Text-to-Image Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2506.21416","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.21416"}},"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/bytedance/xverse","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":10},"by_repo_kind":{"official":{"samples":10,"ran":0,"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":"6d89dc3ce9ef7ba2","entry":"attn_forward","repo":"bytedance/xverse","repo_kind":"official","path":"src/flux/block.py","file_url":"https://github.com/bytedance/xverse/blob/HEAD/src/flux/block.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6d89dc3ce9ef7ba2"}},{"code_sha256_prefix":"6ac74a9618349cce","entry":"calculate_aspect_ratios","repo":"bytedance/xverse","repo_kind":"official","path":"src/utils/data_utils.py","file_url":"https://github.com/bytedance/xverse/blob/HEAD/src/utils/data_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6ac74a9618349cce"}},{"code_sha256_prefix":"bd005c249bf63eec","entry":"get_closest_ratio","repo":"bytedance/xverse","repo_kind":"official","path":"src/utils/data_utils.py","file_url":"https://github.com/bytedance/xverse/blob/HEAD/src/utils/data_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bd005c249bf63eec"}},{"code_sha256_prefix":"2df469f038cac4ca","entry":"get_config","repo":"bytedance/xverse","repo_kind":"official","path":"src/flux/generate.py","file_url":"https://github.com/bytedance/xverse/blob/HEAD/src/flux/generate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2df469f038cac4ca"}},{"code_sha256_prefix":"be5c89b63f30a27f","entry":"get_train_config","repo":"bytedance/xverse","repo_kind":"official","path":"src/utils/data_utils.py","file_url":"https://github.com/bytedance/xverse/blob/HEAD/src/utils/data_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"be5c89b63f30a27f"}},{"code_sha256_prefix":"c202ee494d280f48","entry":"prepare_params","repo":"bytedance/xverse","repo_kind":"official","path":"src/flux/generate.py","file_url":"https://github.com/bytedance/xverse/blob/HEAD/src/flux/generate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c202ee494d280f48"}},{"code_sha256_prefix":"90e17699ece668a1","entry":"prepare_params","repo":"bytedance/xverse","repo_kind":"official","path":"src/flux/transformer.py","file_url":"https://github.com/bytedance/xverse/blob/HEAD/src/flux/transformer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"90e17699ece668a1"}},{"code_sha256_prefix":"75e0eb0c22ca129e","entry":"scaled_dot_product_attention","repo":"bytedance/xverse","repo_kind":"official","path":"src/flux/block.py","file_url":"https://github.com/bytedance/xverse/blob/HEAD/src/flux/block.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"75e0eb0c22ca129e"}},{"code_sha256_prefix":"6c7694a960d7fb34","entry":"set_delta_by_start_end","repo":"bytedance/xverse","repo_kind":"official","path":"src/flux/block.py","file_url":"https://github.com/bytedance/xverse/blob/HEAD/src/flux/block.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6c7694a960d7fb34"}},{"code_sha256_prefix":"53d81af5493825aa","entry":"unpad_input_ids","repo":"bytedance/xverse","repo_kind":"official","path":"src/utils/modulation_utils.py","file_url":"https://github.com/bytedance/xverse/blob/HEAD/src/utils/modulation_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"53d81af5493825aa"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}