{"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/alleviating-distortion-in-image-generation","title":"Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models and Time-Dependent Layer Normalization","arxiv_id":"2406.09416","date":"2024-06-13","proceeding":null,"authors":["Qihao Liu","Zhanpeng Zeng","Ju He","Qihang Yu","Xiaohui Shen","Liang-Chieh Chen"],"abstract":"This paper presents innovative enhancements to diffusion models by integrating a novel multi-resolution network and time-dependent layer normalization. Diffusion models have gained prominence for their effectiveness in high-fidelity image generation. While conventional approaches rely on convolutional U-Net architectures, recent Transformer-based designs have demonstrated superior performance and scalability. However, Transformer architectures, which tokenize input data (via \"patchification\"), face a trade-off between visual fidelity and computational complexity due to the quadratic nature of self-attention operations concerning token length. While larger patch sizes enable attention computation efficiency, they struggle to capture fine-grained visual details, leading to image distortions. To address this challenge, we propose augmenting the Diffusion model with the Multi-Resolution network (DiMR), a framework that refines features across multiple resolutions, progressively enhancing detail from low to high resolution. Additionally, we introduce Time-Dependent Layer Normalization (TD-LN), a parameter-efficient approach that incorporates time-dependent parameters into layer normalization to inject time information and achieve superior performance. Our method's efficacy is demonstrated on the class-conditional ImageNet generation benchmark, where DiMR-XL variants outperform prior diffusion models, setting new state-of-the-art FID scores of 1.70 on ImageNet 256 x 256 and 2.89 on ImageNet 512 x 512. Project page: https://qihao067.github.io/projects/DiMR","url_abs":"https://arxiv.org/abs/2406.09416v2","url_pdf":"https://arxiv.org/pdf/2406.09416v2.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":"alleviating-distortion-in-image-generation","repo_url":"https://github.com/qihao067/DiMR","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"u-net","method_name":"U-Net"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-generation-on-imagenet-256x256","task":"Image Generation","dataset":"ImageNet 256x256","model":"DiMR-G/2R","rank_in_archive_order":30,"of":94,"metrics":{"FID":"1.63"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-imagenet-256x256","task":"Image Generation","dataset":"ImageNet 256x256","model":"DiMR-XL/2R","rank_in_archive_order":34,"of":94,"metrics":{"FID":"1.70"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-imagenet-512x512","task":"Image Generation","dataset":"ImageNet 512x512","model":"DiMR-XL/3R","rank_in_archive_order":38,"of":52,"metrics":{"FID":"2.89"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2406.09416","atlas_url":"https://app.syntology.ai/?focus=2406.09416","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09416"}},"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/qihao067/DiMR","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":2,"ran":8,"unverified":6},"by_repo_kind":{"official":{"samples":16,"ran":10,"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":"9fcdaa6e423e8aa7","entry":"Normalize","repo":"qihao067/DiMR","repo_kind":"official","path":"libs/autoencoder.py","file_url":"https://github.com/qihao067/DiMR/blob/HEAD/libs/autoencoder.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9fcdaa6e423e8aa7"}},{"code_sha256_prefix":"f057bf3471d77c43","entry":"center_crop","repo":"qihao067/DiMR","repo_kind":"official","path":"datasets.py","file_url":"https://github.com/qihao067/DiMR/blob/HEAD/datasets.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f057bf3471d77c43"}},{"code_sha256_prefix":"d29a52dd74b2322a","entry":"centers","repo":"qihao067/DiMR","repo_kind":"official","path":"libs/core/axial_rope.py","file_url":"https://github.com/qihao067/DiMR/blob/HEAD/libs/core/axial_rope.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d29a52dd74b2322a"}},{"code_sha256_prefix":"d35a53bdb646eb7c","entry":"get_sde","repo":"qihao067/DiMR","repo_kind":"official","path":"sde.py","file_url":"https://github.com/qihao067/DiMR/blob/HEAD/sde.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d35a53bdb646eb7c"}},{"code_sha256_prefix":"86c7877e164664bc","entry":"interpolate_fn","repo":"qihao067/DiMR","repo_kind":"official","path":"dpm_solver.py","file_url":"https://github.com/qihao067/DiMR/blob/HEAD/dpm_solver.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"86c7877e164664bc"}},{"code_sha256_prefix":"ace7da590f4070e0","entry":"model_wrapper","repo":"qihao067/DiMR","repo_kind":"official","path":"dpm_solver.py","file_url":"https://github.com/qihao067/DiMR/blob/HEAD/dpm_solver.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ace7da590f4070e0"}},{"code_sha256_prefix":"02c82bdf3494ea71","entry":"mos","repo":"qihao067/DiMR","repo_kind":"official","path":"sde.py","file_url":"https://github.com/qihao067/DiMR/blob/HEAD/sde.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"02c82bdf3494ea71"}},{"code_sha256_prefix":"3137073275f8c21a","entry":"nonlinearity","repo":"qihao067/DiMR","repo_kind":"official","path":"libs/autoencoder.py","file_url":"https://github.com/qihao067/DiMR/blob/HEAD/libs/autoencoder.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3137073275f8c21a"}},{"code_sha256_prefix":"05d1f95a391c0ec3","entry":"random_crop_arr","repo":"qihao067/DiMR","repo_kind":"official","path":"datasets.py","file_url":"https://github.com/qihao067/DiMR/blob/HEAD/datasets.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"05d1f95a391c0ec3"}},{"code_sha256_prefix":"a098b5566baeb748","entry":"rotate_half","repo":"qihao067/DiMR","repo_kind":"official","path":"libs/core/axial_rope.py","file_url":"https://github.com/qihao067/DiMR/blob/HEAD/libs/core/axial_rope.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a098b5566baeb748"}},{"code_sha256_prefix":"f8b4a29a52612a41","entry":"center_crop_arr","repo":"qihao067/DiMR","repo_kind":"official","path":"datasets.py","file_url":"https://github.com/qihao067/DiMR/blob/HEAD/datasets.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f8b4a29a52612a41"}},{"code_sha256_prefix":"507ea4bd829ac4b0","entry":"dct2str","repo":"qihao067/DiMR","repo_kind":"official","path":"utils.py","file_url":"https://github.com/qihao067/DiMR/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"507ea4bd829ac4b0"}},{"code_sha256_prefix":"673862e6d1280a4b","entry":"get_nnet","repo":"qihao067/DiMR","repo_kind":"official","path":"utils.py","file_url":"https://github.com/qihao067/DiMR/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"673862e6d1280a4b"}},{"code_sha256_prefix":"7328f4d3c151e58b","entry":"get_optimizer","repo":"qihao067/DiMR","repo_kind":"official","path":"utils.py","file_url":"https://github.com/qihao067/DiMR/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7328f4d3c151e58b"}},{"code_sha256_prefix":"f97adc1ae5efb785","entry":"make_attn","repo":"qihao067/DiMR","repo_kind":"official","path":"libs/autoencoder.py","file_url":"https://github.com/qihao067/DiMR/blob/HEAD/libs/autoencoder.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f97adc1ae5efb785"}},{"code_sha256_prefix":"4d33c2f525f1b1c0","entry":"stp","repo":"qihao067/DiMR","repo_kind":"official","path":"sde.py","file_url":"https://github.com/qihao067/DiMR/blob/HEAD/sde.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4d33c2f525f1b1c0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}