{"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/latent-wavelet-diffusion-enabling-4k-image","title":"Latent Wavelet Diffusion: Enabling 4K Image Synthesis for Free","arxiv_id":"2506.00433","date":"2025-05-31","proceeding":null,"authors":["Luigi Sigillo","Shengfeng He","Danilo Comminiello"],"abstract":"High-resolution image synthesis remains a core challenge in generative modeling, particularly in balancing computational efficiency with the preservation of fine-grained visual detail. We present Latent Wavelet Diffusion (LWD), a lightweight framework that enables any latent diffusion model to scale to ultra-high-resolution image generation (2K to 4K) for free. LWD introduces three key components: (1) a scale-consistent variational autoencoder objective that enhances the spectral fidelity of latent representations; (2) wavelet energy maps that identify and localize detail-rich spatial regions within the latent space; and (3) a time-dependent masking strategy that focuses denoising supervision on high-frequency components during training. LWD requires no architectural modifications and incurs no additional computational overhead. Despite its simplicity, it consistently improves perceptual quality and reduces FID in ultra-high-resolution image synthesis, outperforming strong baseline models. These results highlight the effectiveness of frequency-aware, signal-driven supervision as a principled and efficient approach for high-resolution generative modeling.","url_abs":"https://arxiv.org/abs/2506.00433v2","url_pdf":"https://arxiv.org/pdf/2506.00433v2.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":[],"tasks":[{"task_slug":"2k","task_name":"2k"},{"task_slug":"4k","task_name":"4k"},{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"latent-diffusion-model","method_name":"Latent Diffusion Model"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2506.00433","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.00433"}},"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":"deterministic:regex_extraction","url":"https://github.com/LuigiSigillo/LatentWaveletDiffusion","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_violates":1,"ran_draft_wrong":1,"unverified":8},"by_repo_kind":{"found_in_text":{"samples":10,"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":"4e3ad3679e5c37b2","entry":"calculate_shift","repo":"LuigiSigillo/LatentWaveletDiffusion","repo_kind":"found_in_text","path":"src/pipeline_flux.py","file_url":"https://github.com/LuigiSigillo/LatentWaveletDiffusion/blob/HEAD/src/pipeline_flux.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4e3ad3679e5c37b2"}},{"code_sha256_prefix":"0b56680ee1708fee","entry":"retrieve_timesteps","repo":"LuigiSigillo/LatentWaveletDiffusion","repo_kind":"found_in_text","path":"src/pipeline_flux.py","file_url":"https://github.com/LuigiSigillo/LatentWaveletDiffusion/blob/HEAD/src/pipeline_flux.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":"0b56680ee1708fee"}},{"code_sha256_prefix":"6fe1dccb17235788","entry":"compute_wavelet_attention","repo":"LuigiSigillo/LatentWaveletDiffusion","repo_kind":"found_in_text","path":"src/new_wav_attn_maps.py","file_url":"https://github.com/LuigiSigillo/LatentWaveletDiffusion/blob/HEAD/src/new_wav_attn_maps.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":"6fe1dccb17235788"}},{"code_sha256_prefix":"23e116cc74ff473e","entry":"decode_and_save","repo":"LuigiSigillo/LatentWaveletDiffusion","repo_kind":"found_in_text","path":"src/train_2k.py","file_url":"https://github.com/LuigiSigillo/LatentWaveletDiffusion/blob/HEAD/src/train_2k.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":"23e116cc74ff473e"}},{"code_sha256_prefix":"75ac92003acbbee0","entry":"get_mask","repo":"LuigiSigillo/LatentWaveletDiffusion","repo_kind":"found_in_text","path":"src/new_wav_attn_maps.py","file_url":"https://github.com/LuigiSigillo/LatentWaveletDiffusion/blob/HEAD/src/new_wav_attn_maps.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":"75ac92003acbbee0"}},{"code_sha256_prefix":"5a6018313fb2afd6","entry":"get_mask_batch","repo":"LuigiSigillo/LatentWaveletDiffusion","repo_kind":"found_in_text","path":"src/new_wav_attn_maps.py","file_url":"https://github.com/LuigiSigillo/LatentWaveletDiffusion/blob/HEAD/src/new_wav_attn_maps.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":"5a6018313fb2afd6"}},{"code_sha256_prefix":"589fc02804855db7","entry":"parse_args","repo":"LuigiSigillo/LatentWaveletDiffusion","repo_kind":"found_in_text","path":"src/train_2k.py","file_url":"https://github.com/LuigiSigillo/LatentWaveletDiffusion/blob/HEAD/src/train_2k.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":"589fc02804855db7"}},{"code_sha256_prefix":"a548e14c1a574df6","entry":"parse_args","repo":"LuigiSigillo/LatentWaveletDiffusion","repo_kind":"found_in_text","path":"src/train_4k.py","file_url":"https://github.com/LuigiSigillo/LatentWaveletDiffusion/blob/HEAD/src/train_4k.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":"a548e14c1a574df6"}},{"code_sha256_prefix":"a5ae6bb2816685a3","entry":"parse_args","repo":"LuigiSigillo/LatentWaveletDiffusion","repo_kind":"found_in_text","path":"src/helpers/cache_latent_codes.py","file_url":"https://github.com/LuigiSigillo/LatentWaveletDiffusion/blob/HEAD/src/helpers/cache_latent_codes.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":"a5ae6bb2816685a3"}},{"code_sha256_prefix":"35767eedf8ca0430","entry":"resize","repo":"LuigiSigillo/LatentWaveletDiffusion","repo_kind":"found_in_text","path":"src/helpers/cache_latent_codes.py","file_url":"https://github.com/LuigiSigillo/LatentWaveletDiffusion/blob/HEAD/src/helpers/cache_latent_codes.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":"35767eedf8ca0430"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}