{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/wavelet-diffusion-models-are-fast-and","title":"Wavelet Diffusion Models are fast and scalable Image Generators","arxiv_id":"2211.16152","date":"2022-11-29","proceeding":"CVPR 2023 1","authors":["Hao Phung","Quan Dao","Anh Tran"],"abstract":"Diffusion models are rising as a powerful solution for high-fidelity image generation, which exceeds GANs in quality in many circumstances. However, their slow training and inference speed is a huge bottleneck, blocking them from being used in real-time applications. A recent DiffusionGAN method significantly decreases the models' running time by reducing the number of sampling steps from thousands to several, but their speeds still largely lag behind the GAN counterparts. This paper aims to reduce the speed gap by proposing a novel wavelet-based diffusion scheme. We extract low-and-high frequency components from both image and feature levels via wavelet decomposition and adaptively handle these components for faster processing while maintaining good generation quality. Furthermore, we propose to use a reconstruction term, which effectively boosts the model training convergence. Experimental results on CelebA-HQ, CIFAR-10, LSUN-Church, and STL-10 datasets prove our solution is a stepping-stone to offering real-time and high-fidelity diffusion models. Our code and pre-trained checkpoints are available at \\url{https://github.com/VinAIResearch/WaveDiff.git}.","url_abs":"https://arxiv.org/abs/2211.16152v2","url_pdf":"https://arxiv.org/pdf/2211.16152v2.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":"wavelet-diffusion-models-are-fast-and","repo_url":"https://github.com/vinairesearch/wavediff","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"AGPL-3.0"}}],"tasks":[{"task_slug":"blocking","task_name":"Blocking"},{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-generation-on-celeba-hq-1024x1024","task":"Image Generation","dataset":"CelebA-HQ 1024x1024","model":"WaveDiff","rank_in_archive_order":4,"of":10,"metrics":{"FID":"5.98","NFE":"2"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-celeba-hq-256x256","task":"Image Generation","dataset":"CelebA-HQ 256x256","model":"WaveDiff","rank_in_archive_order":6,"of":19,"metrics":{"FID":"5.94","NFE":"2","Recall":"0.37"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-celeba-hq-512x512","task":"Image Generation","dataset":"CelebA-HQ 512x512","model":"WaveDiff","rank_in_archive_order":1,"of":1,"metrics":{"FID":"6.40","NFE":"2","Recall":"0.35"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-lsun-churches-256-x-256","task":"Image Generation","dataset":"LSUN Churches 256 x 256","model":"WaveDiff","rank_in_archive_order":17,"of":27,"metrics":{"FID":"5.06","NFE":"4","Recall":"0.40"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-stl-10","task":"Image Generation","dataset":"STL-10","model":"WaveDiff","rank_in_archive_order":7,"of":31,"metrics":{"FID":"12.93","NFE":"4","Recall":"0.41"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2211.16152","atlas_url":"https://app.syntology.ai/?focus=2211.16152","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2211.16152"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2211.16152\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2211.16152"},"call":"get_concepts_for_paper(arxiv_id=\"2211.16152\")"}],"by_repo":[{"repo":"vinairesearch/wavediff","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"53c817e2ac10e4c39fb1531f68ac433f562259a26972d59445ac1e7dcc20b83c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}