{"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/dim-diffusion-mamba-for-efficient-high","title":"DiM: Diffusion Mamba for Efficient High-Resolution Image Synthesis","arxiv_id":"2405.14224","date":"2024-05-23","proceeding":null,"authors":["Yao Teng","Yue Wu","Han Shi","Xuefei Ning","Guohao Dai","Yu Wang","Zhenguo Li","Xihui Liu"],"abstract":"Diffusion models have achieved great success in image generation, with the backbone evolving from U-Net to Vision Transformers. However, the computational cost of Transformers is quadratic to the number of tokens, leading to significant challenges when dealing with high-resolution images. In this work, we propose Diffusion Mamba (DiM), which combines the efficiency of Mamba, a sequence model based on State Space Models (SSM), with the expressive power of diffusion models for efficient high-resolution image synthesis. To address the challenge that Mamba cannot generalize to 2D signals, we make several architecture designs including multi-directional scans, learnable padding tokens at the end of each row and column, and lightweight local feature enhancement. Our DiM architecture achieves inference-time efficiency for high-resolution images. In addition, to further improve training efficiency for high-resolution image generation with DiM, we investigate \"weak-to-strong\" training strategy that pretrains DiM on low-resolution images ($256\\times 256$) and then finetune it on high-resolution images ($512 \\times 512$). We further explore training-free upsampling strategies to enable the model to generate higher-resolution images (e.g., $1024\\times 1024$ and $1536\\times 1536$) without further fine-tuning. Experiments demonstrate the effectiveness and efficiency of our DiM. The code of our work is available here: {\\url{https://github.com/tyshiwo1/DiM-DiffusionMamba/}}.","url_abs":"https://arxiv.org/abs/2405.14224v2","url_pdf":"https://arxiv.org/pdf/2405.14224v2.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":"dim-diffusion-mamba-for-efficient-high","repo_url":"https://github.com/tyshiwo1/dim-diffusionmamba","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"mamba","task_name":"Mamba"},{"task_slug":"state-space-models","task_name":"State Space Models"}],"methods":[{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"u-net","method_name":"U-Net"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.14224","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14224"}},"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/tyshiwo1/dim-diffusionmamba","reach":{"status":"ok"}}],"summary":{"ran":5,"ran_honours":1,"unverified":3},"by_repo_kind":{"official":{"samples":9,"ran":6,"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":"86c7877e164664bc","entry":"interpolate_fn","repo":"tyshiwo1/dim-diffusionmamba","repo_kind":"official","path":"dpm_solver_pp.py","file_url":"https://github.com/tyshiwo1/dim-diffusionmamba/blob/HEAD/dpm_solver_pp.py","link_basis":"harvester_set","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":"86c7877e164664bc"}},{"code_sha256_prefix":"18e2f1d8dba04a34","entry":"model_wrapper","repo":"tyshiwo1/dim-diffusionmamba","repo_kind":"official","path":"dpm_solver_pp.py","file_url":"https://github.com/tyshiwo1/dim-diffusionmamba/blob/HEAD/dpm_solver_pp.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":"18e2f1d8dba04a34"}},{"code_sha256_prefix":"876b54273bf5ba75","entry":"model_wrapper","repo":"tyshiwo1/dim-diffusionmamba","repo_kind":"official","path":"dpm_solver_pytorch.py","file_url":"https://github.com/tyshiwo1/dim-diffusionmamba/blob/HEAD/dpm_solver_pytorch.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":"876b54273bf5ba75"}},{"code_sha256_prefix":"f3e8a4d9233487be","entry":"mos","repo":"tyshiwo1/dim-diffusionmamba","repo_kind":"official","path":"sde.py","file_url":"https://github.com/tyshiwo1/dim-diffusionmamba/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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f3e8a4d9233487be"}},{"code_sha256_prefix":"2ee6e353f1dd4cf3","entry":"stable_diffusion_beta_schedule","repo":"tyshiwo1/dim-diffusionmamba","repo_kind":"official","path":"eval_ldm_discrete.py","file_url":"https://github.com/tyshiwo1/dim-diffusionmamba/blob/HEAD/eval_ldm_discrete.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2ee6e353f1dd4cf3"}},{"code_sha256_prefix":"22379353b48c046e","entry":"stp","repo":"tyshiwo1/dim-diffusionmamba","repo_kind":"official","path":"eval_ldm_discrete.py","file_url":"https://github.com/tyshiwo1/dim-diffusionmamba/blob/HEAD/eval_ldm_discrete.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":"22379353b48c046e"}},{"code_sha256_prefix":"62391afb6538762f","entry":"get_sde","repo":"tyshiwo1/dim-diffusionmamba","repo_kind":"official","path":"sde.py","file_url":"https://github.com/tyshiwo1/dim-diffusionmamba/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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"62391afb6538762f"}},{"code_sha256_prefix":"4423f3550826f012","entry":"get_skip","repo":"tyshiwo1/dim-diffusionmamba","repo_kind":"official","path":"eval_ldm_discrete.py","file_url":"https://github.com/tyshiwo1/dim-diffusionmamba/blob/HEAD/eval_ldm_discrete.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4423f3550826f012"}},{"code_sha256_prefix":"4d33c2f525f1b1c0","entry":"stp","repo":"tyshiwo1/dim-diffusionmamba","repo_kind":"official","path":"sde.py","file_url":"https://github.com/tyshiwo1/dim-diffusionmamba/blob/HEAD/sde.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4d33c2f525f1b1c0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}