{"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/hunyuancustom-a-multimodal-driven","title":"HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation","arxiv_id":"2505.04512","date":"2025-05-07","proceeding":null,"authors":["Teng Hu","Zhentao Yu","Zhengguang Zhou","Sen Liang","Yuan Zhou","Qin Lin","Qinglin Lu"],"abstract":"Customized video generation aims to produce videos featuring specific subjects under flexible user-defined conditions, yet existing methods often struggle with identity consistency and limited input modalities. In this paper, we propose HunyuanCustom, a multi-modal customized video generation framework that emphasizes subject consistency while supporting image, audio, video, and text conditions. Built upon HunyuanVideo, our model first addresses the image-text conditioned generation task by introducing a text-image fusion module based on LLaVA for enhanced multi-modal understanding, along with an image ID enhancement module that leverages temporal concatenation to reinforce identity features across frames. To enable audio- and video-conditioned generation, we further propose modality-specific condition injection mechanisms: an AudioNet module that achieves hierarchical alignment via spatial cross-attention, and a video-driven injection module that integrates latent-compressed conditional video through a patchify-based feature-alignment network. Extensive experiments on single- and multi-subject scenarios demonstrate that HunyuanCustom significantly outperforms state-of-the-art open- and closed-source methods in terms of ID consistency, realism, and text-video alignment. Moreover, we validate its robustness across downstream tasks, including audio and video-driven customized video generation. Our results highlight the effectiveness of multi-modal conditioning and identity-preserving strategies in advancing controllable video generation. All the code and models are available at https://hunyuancustom.github.io.","url_abs":"https://arxiv.org/abs/2505.04512v2","url_pdf":"https://arxiv.org/pdf/2505.04512v2.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":"hunyuancustom-a-multimodal-driven","repo_url":"https://github.com/tencent-hunyuan/hunyuancustom","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"human-domain-subject-to-video","task_name":"Human-Domain Subject-to-Video"},{"task_slug":"single-domain-subject-to-video","task_name":"Single-Domain Subject-to-Video"},{"task_slug":"video-alignment","task_name":"Video Alignment"},{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.04512","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.04512"}},"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/tencent-hunyuan/hunyuancustom","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{},"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":2,"samples":[{"code_sha256_prefix":"bea2d776a332f2b0","entry":"rescale_noise_cfg","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":"bea2d776a332f2b0"}},{"code_sha256_prefix":"f3a81898d239b163","entry":"retrieve_timesteps","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":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"f3a81898d239b163"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}