{"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/moma-multimodal-llm-adapter-for-fast","title":"MoMA: Multimodal LLM Adapter for Fast Personalized Image Generation","arxiv_id":"2404.05674","date":"2024-04-08","proceeding":null,"authors":["Kunpeng Song","Yizhe Zhu","Bingchen Liu","Qing Yan","Ahmed Elgammal","Xiao Yang"],"abstract":"In this paper, we present MoMA: an open-vocabulary, training-free personalized image model that boasts flexible zero-shot capabilities. As foundational text-to-image models rapidly evolve, the demand for robust image-to-image translation grows. Addressing this need, MoMA specializes in subject-driven personalized image generation. Utilizing an open-source, Multimodal Large Language Model (MLLM), we train MoMA to serve a dual role as both a feature extractor and a generator. This approach effectively synergizes reference image and text prompt information to produce valuable image features, facilitating an image diffusion model. To better leverage the generated features, we further introduce a novel self-attention shortcut method that efficiently transfers image features to an image diffusion model, improving the resemblance of the target object in generated images. Remarkably, as a tuning-free plug-and-play module, our model requires only a single reference image and outperforms existing methods in generating images with high detail fidelity, enhanced identity-preservation and prompt faithfulness. Our work is open-source, thereby providing universal access to these advancements.","url_abs":"https://arxiv.org/abs/2404.05674v1","url_pdf":"https://arxiv.org/pdf/2404.05674v1.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":"moma-multimodal-llm-adapter-for-fast","repo_url":"https://github.com/bytedance/MoMA","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"image-to-image-translation","task_name":"Image-to-Image Translation"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"multimodal-large-language-model","task_name":"Multimodal Large Language Model"},{"task_slug":"personalized-image-generation","task_name":"Personalized Image Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2404.05674","atlas_url":"https://app.syntology.ai/?focus=2404.05674","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05674"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/MoMA","reach":{"status":"ok"}}],"summary":{"ran":1,"unverified":3},"by_repo_kind":{"official":{"samples":4,"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":4,"samples":[{"code_sha256_prefix":"de3717332607a97b","entry":"show_PIL_image","repo":"bytedance/MoMA","repo_kind":"official","path":"model_lib/utils.py","file_url":"https://github.com/bytedance/MoMA/blob/HEAD/model_lib/utils.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":"de3717332607a97b"}},{"code_sha256_prefix":"fb5cf2ab77ae79a2","entry":"add_function","repo":"bytedance/MoMA","repo_kind":"official","path":"model_lib/modules.py","file_url":"https://github.com/bytedance/MoMA/blob/HEAD/model_lib/modules.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fb5cf2ab77ae79a2"}},{"code_sha256_prefix":"72a0f5324a14e3d0","entry":"get_mask_from_cross","repo":"bytedance/MoMA","repo_kind":"official","path":"model_lib/attention_processor.py","file_url":"https://github.com/bytedance/MoMA/blob/HEAD/model_lib/attention_processor.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"72a0f5324a14e3d0"}},{"code_sha256_prefix":"815e9821a0874f7f","entry":"get_subject_idx","repo":"bytedance/MoMA","repo_kind":"official","path":"model_lib/moMA_generator.py","file_url":"https://github.com/bytedance/MoMA/blob/HEAD/model_lib/moMA_generator.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"815e9821a0874f7f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}