{"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/diffusion-4k-ultra-high-resolution-image","title":"Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Models","arxiv_id":"2503.18352","date":"2025-03-24","proceeding":"CVPR 2025 1","authors":["Jinjin Zhang","Qiuyu Huang","Junjie Liu","Xiefan Guo","Di Huang"],"abstract":"In this paper, we present Diffusion-4K, a novel framework for direct ultra-high-resolution image synthesis using text-to-image diffusion models. The core advancements include: (1) Aesthetic-4K Benchmark: addressing the absence of a publicly available 4K image synthesis dataset, we construct Aesthetic-4K, a comprehensive benchmark for ultra-high-resolution image generation. We curated a high-quality 4K dataset with carefully selected images and captions generated by GPT-4o. Additionally, we introduce GLCM Score and Compression Ratio metrics to evaluate fine details, combined with holistic measures such as FID, Aesthetics and CLIPScore for a comprehensive assessment of ultra-high-resolution images. (2) Wavelet-based Fine-tuning: we propose a wavelet-based fine-tuning approach for direct training with photorealistic 4K images, applicable to various latent diffusion models, demonstrating its effectiveness in synthesizing highly detailed 4K images. Consequently, Diffusion-4K achieves impressive performance in high-quality image synthesis and text prompt adherence, especially when powered by modern large-scale diffusion models (e.g., SD3-2B and Flux-12B). Extensive experimental results from our benchmark demonstrate the superiority of Diffusion-4K in ultra-high-resolution image synthesis.","url_abs":"https://arxiv.org/abs/2503.18352v2","url_pdf":"https://arxiv.org/pdf/2503.18352v2.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":"diffusion-4k-ultra-high-resolution-image","repo_url":"https://github.com/zhang0jhon/diffusion-4k","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"4k","task_name":"4k"},{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.18352","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}