{"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/frecas-efficient-higher-resolution-image","title":"FreCaS: Efficient Higher-Resolution Image Generation via Frequency-aware Cascaded Sampling","arxiv_id":"2410.18410","date":"2024-10-24","proceeding":null,"authors":["Zhengqiang Zhang","Ruihuang Li","Lei Zhang"],"abstract":"While image generation with diffusion models has achieved a great success, generating images of higher resolution than the training size remains a challenging task due to the high computational cost. Current methods typically perform the entire sampling process at full resolution and process all frequency components simultaneously, contradicting with the inherent coarse-to-fine nature of latent diffusion models and wasting computations on processing premature high-frequency details at early diffusion stages. To address this issue, we introduce an efficient $\\textbf{Fre}$quency-aware $\\textbf{Ca}$scaded $\\textbf{S}$ampling framework, $\\textbf{FreCaS}$ in short, for higher-resolution image generation. FreCaS decomposes the sampling process into cascaded stages with gradually increased resolutions, progressively expanding frequency bands and refining the corresponding details. We propose an innovative frequency-aware classifier-free guidance (FA-CFG) strategy to assign different guidance strengths for different frequency components, directing the diffusion model to add new details in the expanded frequency domain of each stage. Additionally, we fuse the cross-attention maps of previous and current stages to avoid synthesizing unfaithful layouts. Experiments demonstrate that FreCaS significantly outperforms state-of-the-art methods in image quality and generation speed. In particular, FreCaS is about 2.86$\\times$ and 6.07$\\times$ faster than ScaleCrafter and DemoFusion in generating a 2048$\\times$2048 image using a pre-trained SDXL model and achieves an FID$_b$ improvement of 11.6 and 3.7, respectively. FreCaS can be easily extended to more complex models such as SD3. The source code of FreCaS can be found at $\\href{\\text{https://github.com/xtudbxk/FreCaS}}{https://github.com/xtudbxk/FreCaS}$.","url_abs":"https://arxiv.org/abs/2410.18410v1","url_pdf":"https://arxiv.org/pdf/2410.18410v1.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":"frecas-efficient-higher-resolution-image","repo_url":"https://github.com/xtudbxk/frecas","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"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.18410","atlas_url":"https://app.syntology.ai/?focus=2410.18410","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.18410"}},"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/xtudbxk/frecas","reach":{"status":"ok"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"ran":0,"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":7,"samples":[{"code_sha256_prefix":"68a2e4bc10601722","entry":"freq_decompose","repo":"xtudbxk/frecas","repo_kind":"official","path":"utils/facfg_wrapper.py","file_url":"https://github.com/xtudbxk/frecas/blob/HEAD/utils/facfg_wrapper.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":"68a2e4bc10601722"}},{"code_sha256_prefix":"fdc2ecb512c95b13","entry":"get_next_starttimestep","repo":"xtudbxk/frecas","repo_kind":"official","path":"utils/scheduler_wrapper.py","file_url":"https://github.com/xtudbxk/frecas/blob/HEAD/utils/scheduler_wrapper.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":"fdc2ecb512c95b13"}},{"code_sha256_prefix":"21d83fe55d01050d","entry":"get_next_starttimestep_rf","repo":"xtudbxk/frecas","repo_kind":"official","path":"utils/scheduler_wrapper.py","file_url":"https://github.com/xtudbxk/frecas/blob/HEAD/utils/scheduler_wrapper.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":"21d83fe55d01050d"}},{"code_sha256_prefix":"530bc361f235bab9","entry":"obtain_origin","repo":"xtudbxk/frecas","repo_kind":"official","path":"utils/wrapper_utils.py","file_url":"https://github.com/xtudbxk/frecas/blob/HEAD/utils/wrapper_utils.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":"530bc361f235bab9"}},{"code_sha256_prefix":"00153ea284da6e39","entry":"sd21_vae_encode","repo":"xtudbxk/frecas","repo_kind":"official","path":"utils/sd_utils.py","file_url":"https://github.com/xtudbxk/frecas/blob/HEAD/utils/sd_utils.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":"00153ea284da6e39"}},{"code_sha256_prefix":"22c6bd4c45c0c13f","entry":"unwrap","repo":"xtudbxk/frecas","repo_kind":"official","path":"utils/wrapper_utils.py","file_url":"https://github.com/xtudbxk/frecas/blob/HEAD/utils/wrapper_utils.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":"22c6bd4c45c0c13f"}},{"code_sha256_prefix":"d6e7f4b172e9b341","entry":"wrap","repo":"xtudbxk/frecas","repo_kind":"official","path":"utils/wrapper_utils.py","file_url":"https://github.com/xtudbxk/frecas/blob/HEAD/utils/wrapper_utils.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":"d6e7f4b172e9b341"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}