{"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/diffusehigh-training-free-progressive-high","title":"DiffuseHigh: Training-free Progressive High-Resolution Image Synthesis through Structure Guidance","arxiv_id":"2406.18459","date":"2024-06-26","proceeding":null,"authors":["Younghyun Kim","Geunmin Hwang","Junyu Zhang","Eunbyung Park"],"abstract":"Large-scale generative models, such as text-to-image diffusion models, have garnered widespread attention across diverse domains due to their creative and high-fidelity image generation. Nonetheless, existing large-scale diffusion models are confined to generating images of up to 1K resolution, which is far from meeting the demands of contemporary commercial applications. Directly sampling higher-resolution images often yields results marred by artifacts such as object repetition and distorted shapes. Addressing the aforementioned issues typically necessitates training or fine-tuning models on higher-resolution datasets. However, this poses a formidable challenge due to the difficulty in collecting large-scale high-resolution images and substantial computational resources. While several preceding works have proposed alternatives to bypass the cumbersome training process, they often fail to produce convincing results. In this work, we probe the generative ability of diffusion models at higher resolution beyond their original capability and propose a novel progressive approach that fully utilizes generated low-resolution images to guide the generation of higher-resolution images. Our method obviates the need for additional training or fine-tuning which significantly lowers the burden of computational costs. Extensive experiments and results validate the efficiency and efficacy of our method. Project page: https://yhyun225.github.io/DiffuseHigh/","url_abs":"https://arxiv.org/abs/2406.18459v5","url_pdf":"https://arxiv.org/pdf/2406.18459v5.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":"diffusehigh-training-free-progressive-high","repo_url":"https://github.com/yhyun225/DiffuseHigh","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.18459","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18459"}},"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/yhyun225/DiffuseHigh","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"ran":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":"bea2d776a332f2b0","entry":"rescale_noise_cfg","repo":"yhyun225/DiffuseHigh","repo_kind":"official","path":"pipeline_diffusehigh_sdxl.py","file_url":"https://github.com/yhyun225/DiffuseHigh/blob/HEAD/pipeline_diffusehigh_sdxl.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bea2d776a332f2b0"}},{"code_sha256_prefix":"35717b791550ecb2","entry":"retrieve_timesteps","repo":"yhyun225/DiffuseHigh","repo_kind":"official","path":"pipeline_diffusehigh_sdxl.py","file_url":"https://github.com/yhyun225/DiffuseHigh/blob/HEAD/pipeline_diffusehigh_sdxl.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"35717b791550ecb2"}},{"code_sha256_prefix":"e036b8a955111950","entry":"gaussian_blur_image_sharpening","repo":"yhyun225/DiffuseHigh","repo_kind":"official","path":"pipeline_diffusehigh_sdxl.py","file_url":"https://github.com/yhyun225/DiffuseHigh/blob/HEAD/pipeline_diffusehigh_sdxl.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e036b8a955111950"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}