{"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/hunyuan-dit-a-powerful-multi-resolution","title":"Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding","arxiv_id":"2405.08748","date":"2024-05-14","proceeding":null,"authors":["Zhimin Li","Jianwei Zhang","Qin Lin","Jiangfeng Xiong","Yanxin Long","Xinchi Deng","Yingfang Zhang","Xingchao Liu","Minbin Huang","Zedong Xiao","Dayou Chen","Jiajun He","Jiahao Li","Wenyue Li","Chen Zhang","Rongwei Quan","Jianxiang Lu","Jiabin Huang","Xiaoyan Yuan","Xiaoxiao Zheng","Yixuan Li","Jihong Zhang","Chao Zhang","Meng Chen","Jie Liu","Zheng Fang","Weiyan Wang","Jinbao Xue","Yangyu Tao","Jianchen Zhu","Kai Liu","Sihuan Lin","Yifu Sun","Yun Li","Dongdong Wang","Mingtao Chen","Zhichao Hu","Xiao Xiao","Yan Chen","Yuhong Liu","Wei Liu","Di Wang","Yong Yang","Jie Jiang","Qinglin Lu"],"abstract":"We present Hunyuan-DiT, a text-to-image diffusion transformer with fine-grained understanding of both English and Chinese. To construct Hunyuan-DiT, we carefully design the transformer structure, text encoder, and positional encoding. We also build from scratch a whole data pipeline to update and evaluate data for iterative model optimization. For fine-grained language understanding, we train a Multimodal Large Language Model to refine the captions of the images. Finally, Hunyuan-DiT can perform multi-turn multimodal dialogue with users, generating and refining images according to the context. Through our holistic human evaluation protocol with more than 50 professional human evaluators, Hunyuan-DiT sets a new state-of-the-art in Chinese-to-image generation compared with other open-source models. Code and pretrained models are publicly available at github.com/Tencent/HunyuanDiT","url_abs":"https://arxiv.org/abs/2405.08748v1","url_pdf":"https://arxiv.org/pdf/2405.08748v1.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":"hunyuan-dit-a-powerful-multi-resolution","repo_url":"https://github.com/tencent/hunyuandit","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"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":"model-optimization","task_name":"Model Optimization"},{"task_slug":"multimodal-large-language-model","task_name":"Multimodal Large Language Model"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2405.08748","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.08748"}},"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/hunyuandit","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":7,"ran_draft_wrong":1,"unverified":4},"by_repo_kind":{"official":{"samples":12,"ran":8,"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":12,"samples":[{"code_sha256_prefix":"d214740896301d88","entry":"get_canny","repo":"tencent/hunyuandit","repo_kind":"official","path":"hydit/train_deepspeed_controlnet.py","file_url":"https://github.com/tencent/hunyuandit/blob/HEAD/hydit/train_deepspeed_controlnet.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":"d214740896301d88"}},{"code_sha256_prefix":"4ca7234be2368949","entry":"get_files_with_extension","repo":"tencent/hunyuandit","repo_kind":"official","path":"app/hydit_app.py","file_url":"https://github.com/tencent/hunyuandit/blob/HEAD/app/hydit_app.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":"4ca7234be2368949"}},{"code_sha256_prefix":"0a673e09d7e2b07d","entry":"get_image_md5","repo":"tencent/hunyuandit","repo_kind":"official","path":"app/multiTurnT2I_app.py","file_url":"https://github.com/tencent/hunyuandit/blob/HEAD/app/multiTurnT2I_app.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":"0a673e09d7e2b07d"}},{"code_sha256_prefix":"a8e8a949f9510a56","entry":"get_standard_shape","repo":"tencent/hunyuandit","repo_kind":"official","path":"hydit/inference_controlnet.py","file_url":"https://github.com/tencent/hunyuandit/blob/HEAD/hydit/inference_controlnet.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":"a8e8a949f9510a56"}},{"code_sha256_prefix":"1a675900bfebf77e","entry":"get_strings","repo":"tencent/hunyuandit","repo_kind":"official","path":"app/multiTurnT2I_app.py","file_url":"https://github.com/tencent/hunyuandit/blob/HEAD/app/multiTurnT2I_app.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":"1a675900bfebf77e"}},{"code_sha256_prefix":"b8ae69ae303b5554","entry":"image_to_base64","repo":"tencent/hunyuandit","repo_kind":"official","path":"app/multiTurnT2I_app.py","file_url":"https://github.com/tencent/hunyuandit/blob/HEAD/app/multiTurnT2I_app.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":"b8ae69ae303b5554"}},{"code_sha256_prefix":"bea2d776a332f2b0","entry":"rescale_noise_cfg","repo":"tencent/hunyuandit","repo_kind":"official","path":"hydit/diffusion/pipeline_controlnet.py","file_url":"https://github.com/tencent/hunyuandit/blob/HEAD/hydit/diffusion/pipeline_controlnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bea2d776a332f2b0"}},{"code_sha256_prefix":"02d43c51b3337304","entry":"save_checkpoint","repo":"tencent/hunyuandit","repo_kind":"official","path":"hydit/train_deepspeed_controlnet.py","file_url":"https://github.com/tencent/hunyuandit/blob/HEAD/hydit/train_deepspeed_controlnet.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":"02d43c51b3337304"}},{"code_sha256_prefix":"02a702c78a616b85","entry":"deepspeed_config_from_args","repo":"tencent/hunyuandit","repo_kind":"official","path":"hydit/ds_config.py","file_url":"https://github.com/tencent/hunyuandit/blob/HEAD/hydit/ds_config.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":"02a702c78a616b85"}},{"code_sha256_prefix":"1efb40b2d9d466c0","entry":"generate_metadata","repo":"tencent/hunyuandit","repo_kind":"official","path":"app/hydit_app.py","file_url":"https://github.com/tencent/hunyuandit/blob/HEAD/app/hydit_app.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":"1efb40b2d9d466c0"}},{"code_sha256_prefix":"cbed30d63c5042c9","entry":"get_pipeline","repo":"tencent/hunyuandit","repo_kind":"official","path":"hydit/inference_controlnet.py","file_url":"https://github.com/tencent/hunyuandit/blob/HEAD/hydit/inference_controlnet.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":"cbed30d63c5042c9"}},{"code_sha256_prefix":"a2799bac45bb59c9","entry":"model_var_type","repo":"tencent/hunyuandit","repo_kind":"official","path":"hydit/config.py","file_url":"https://github.com/tencent/hunyuandit/blob/HEAD/hydit/config.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":"a2799bac45bb59c9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}