{"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/hiprompt-tuning-free-higher-resolution","title":"HiPrompt: Tuning-free Higher-Resolution Generation with Hierarchical MLLM Prompts","arxiv_id":"2409.02919","date":"2024-09-04","proceeding":null,"authors":["Xinyu Liu","Yingqing He","Lanqing Guo","Xiang Li","Bu Jin","Peng Li","Yan Li","Chi-Min Chan","Qifeng Chen","Wei Xue","Wenhan Luo","Qifeng Liu","Yike Guo"],"abstract":"The potential for higher-resolution image generation using pretrained diffusion models is immense, yet these models often struggle with issues of object repetition and structural artifacts especially when scaling to 4K resolution and higher. We figure out that the problem is caused by that, a single prompt for the generation of multiple scales provides insufficient efficacy. In response, we propose HiPrompt, a new tuning-free solution that tackles the above problems by introducing hierarchical prompts. The hierarchical prompts offer both global and local guidance. Specifically, the global guidance comes from the user input that describes the overall content, while the local guidance utilizes patch-wise descriptions from MLLMs to elaborately guide the regional structure and texture generation. Furthermore, during the inverse denoising process, the generated noise is decomposed into low- and high-frequency spatial components. These components are conditioned on multiple prompt levels, including detailed patch-wise descriptions and broader image-level prompts, facilitating prompt-guided denoising under hierarchical semantic guidance. It further allows the generation to focus more on local spatial regions and ensures the generated images maintain coherent local and global semantics, structures, and textures with high definition. Extensive experiments demonstrate that HiPrompt outperforms state-of-the-art works in higher-resolution image generation, significantly reducing object repetition and enhancing structural quality.","url_abs":"https://arxiv.org/abs/2409.02919v3","url_pdf":"https://arxiv.org/pdf/2409.02919v3.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":"hiprompt-tuning-free-higher-resolution","repo_url":"https://github.com/Liuxinyv/HiPrompt","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"4k","task_name":"4k"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"texture-synthesis","task_name":"Texture Synthesis"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2409.02919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.02919"}},"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/Liuxinyv/HiPrompt","reach":{"status":"ok"}}],"summary":{"ran":3,"ran_draft_wrong":4,"ran_honours":2},"by_repo_kind":{"official":{"samples":9,"ran":9,"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":9,"samples":[{"code_sha256_prefix":"d58bee44f70684eb","entry":"auto_configure_device_map","repo":"Liuxinyv/HiPrompt","repo_kind":"official","path":"share4v_infer.py","file_url":"https://github.com/Liuxinyv/HiPrompt/blob/HEAD/share4v_infer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d58bee44f70684eb"}},{"code_sha256_prefix":"4ecae84676eeb6cf","entry":"eval_model_share","repo":"Liuxinyv/HiPrompt","repo_kind":"official","path":"share4v_infer.py","file_url":"https://github.com/Liuxinyv/HiPrompt/blob/HEAD/share4v_infer.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":"4ecae84676eeb6cf"}},{"code_sha256_prefix":"d62a181623d1f0cf","entry":"gaussian_filter","repo":"Liuxinyv/HiPrompt","repo_kind":"official","path":"hiprompt_sdxl_llava.py","file_url":"https://github.com/Liuxinyv/HiPrompt/blob/HEAD/hiprompt_sdxl_llava.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d62a181623d1f0cf"}},{"code_sha256_prefix":"426a6e743be91d5f","entry":"gaussian_kernel","repo":"Liuxinyv/HiPrompt","repo_kind":"official","path":"hiprompt_sdxl_llava.py","file_url":"https://github.com/Liuxinyv/HiPrompt/blob/HEAD/hiprompt_sdxl_llava.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"426a6e743be91d5f"}},{"code_sha256_prefix":"42a46570620cd9fa","entry":"get_chunk","repo":"Liuxinyv/HiPrompt","repo_kind":"official","path":"LLaVA/llava/eval/model_vqa.py","file_url":"https://github.com/Liuxinyv/HiPrompt/blob/HEAD/LLaVA/llava/eval/model_vqa.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"42a46570620cd9fa"}},{"code_sha256_prefix":"9b3c1cb391672ccb","entry":"load_image","repo":"Liuxinyv/HiPrompt","repo_kind":"official","path":"LLaVA/predict.py","file_url":"https://github.com/Liuxinyv/HiPrompt/blob/HEAD/LLaVA/predict.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"code_sha256_prefix":"bcc85aef36be4636","entry":"make_frame_hybrid","repo":"Liuxinyv/HiPrompt","repo_kind":"official","path":"views/hybrid.py","file_url":"https://github.com/Liuxinyv/HiPrompt/blob/HEAD/views/hybrid.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":"bcc85aef36be4636"}},{"code_sha256_prefix":"bea2d776a332f2b0","entry":"rescale_noise_cfg","repo":"Liuxinyv/HiPrompt","repo_kind":"official","path":"hiprompt_sdxl_llava.py","file_url":"https://github.com/Liuxinyv/HiPrompt/blob/HEAD/hiprompt_sdxl_llava.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":"076c252c52cbb161","entry":"split_list","repo":"Liuxinyv/HiPrompt","repo_kind":"official","path":"LLaVA/llava/eval/model_vqa.py","file_url":"https://github.com/Liuxinyv/HiPrompt/blob/HEAD/LLaVA/llava/eval/model_vqa.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"076c252c52cbb161"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}