{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:47:27Z","timestamp":1773802047831,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"14","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Ultra-high-resolution (UHR) text-to-image synthesis faces significant hurdles, including immense computational costs and a scarcity of training data. To address these, we introduce RealUHR, an efficient and scalable framework for generating photorealistic 4K images. At its core, RealUHR employs a Patch-Cascade Flow Matching pipeline that ensures global coherence without costly patch fusion by initiating generation from a semantically meaningful structure. This enables highly efficient, few-step inference for independent patches. Our key contribution is Guidance-Consistent Adaptation (GCA), a novel two-stage strategy to resolve the fundamental objective mismatch in guidance-distilled models. GCA allows powerful backbones like FLUX to be effectively adapted for patch-aware UHR synthesis. The framework's detail-rendering capabilities are further enhanced by a non-uniform time schedule. Experiments show that RealUHR establishes superior performance in both quality and efficiency, and excels in zero-shot applications such as creative up-sampling and generative artifact suppression.<\/jats:p>","DOI":"10.1609\/aaai.v40i14.38211","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:11:57Z","timestamp":1773792717000},"page":"12204-12212","source":"Crossref","is-referenced-by-count":0,"title":["RealUHR: Harnessing Patch-Cascade Flows for Photorealistic Ultra-High-Resolution Synthesis"],"prefix":"10.1609","volume":"40","author":[{"given":"Yongsheng","family":"Yu","sequence":"first","affiliation":[]},{"given":"Haitian","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Zhe","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Connelly","family":"Barnes","sequence":"additional","affiliation":[]},{"given":"Yuqian","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Zhifei","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Jiebo","family":"Luo","sequence":"additional","affiliation":[]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/38211\/42173","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/38211\/42173","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:11:57Z","timestamp":1773792717000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/38211"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i14.38211","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}