Abstract:
High-resolution image generation with Generative Artificial Intelligence (GenAl) has immense potential but, due to the enormous capital investment required for training, ...Show MoreMetadata
Abstract:
High-resolution image generation with Generative Artificial Intelligence (GenAl) has immense potential but, due to the enormous capital investment required for training, it is increasimgly centralised to a few large corporations, and hidden behind paywalls. This paper aims to democratise high-resolution GenAl by advancing the frontier of high-resolution generation while remaining accessible to a broad audience. We demonstrate that existing Latent Diffusion Models (LDMs) possess untapped potential for higher-resolution image generation. Our novel DemoFusion framework seamlessly extends open-source GenAl models, employing Progressive Upscaling, Skip Residual, and Di-lated Sampling mechanisms to achieve higher-resolution image generation. The progressive nature of DemoFusion requires more passes, but the intermediate results can serve as “previews”, facilitating rapid prompt iteration.
Date of Conference: 16-22 June 2024
Date Added to IEEE Xplore: 16 September 2024
ISBN Information:
ISSN Information:
Funding Agency:
Citations are not available for this document.
Contents Cites in Papers - |
Cites in Papers - IEEE (3)
Select All
1.
Zhiyu Qu, Lan Yang, Honggang Zhang, Tao Xiang, Kaiyue Pang, Yi-Zhe Song, "Wired Perspectives: Multi-View Wire Art Embraces Generative AI", 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp.6149-6158, 2024.
2.
Moayed Haji-Ali, Guha Balakrishnan, Vicente Ordonez, "ElasticDiffusion: Training-Free Arbitrary Size Image Generation Through Global-Local Content Separation", 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp.6603-6612, 2024.
3.
Yanhao Li, Quentin Bammey, Marina Gardella, Tina Nikoukhah, Jean-Michel Morel, Miguel Colom, Rafael Grompone Von Gioi, "MaskSim: Detection of synthetic images by masked spectrum similarity analysis", 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp.3855-3865, 2024.
Cites in Papers - Other Publishers (4)
1.
Junsong Chen, Chongjian Ge, Enze Xie, Yue Wu, Lewei Yao, Xiaozhe Ren, Zhongdao Wang, Ping Luo, Huchuan Lu, Zhenguo Li, "PIXART-\\\\Sigma : Weak-to-Strong Training of\\xa0Diffusion Transformer for\\xa04K Text-to-Image Generation", Computer Vision – ECCV 2024, vol.15090, pp.74, 2025.
2.
Zhuoyi Yang, Heyang Jiang, Wenyi Hong, Jiayan Teng, Wendi Zheng, Yuxiao Dong, Ming Ding, Jie Tang, "Inf-DiT: Upsampling Any-Resolution Image with\\xa0Memory-Efficient Diffusion Transformer", Computer Vision – ECCV 2024, vol.15141, pp.141, 2025.
3.
Shen Zhang, Zhaowei Chen, Zhenyu Zhao, Yuhao Chen, Yao Tang, Jiajun Liang, "HiDiffusion: Unlocking Higher-Resolution Creativity and\\xa0Efficiency in\\xa0Pretrained Diffusion Models", Computer Vision – ECCV 2024, vol.15109, pp.145, 2025.
4.
Zhihang Lin, Mingbao Lin, Meng Zhao, Rongrong Ji, "AccDiffusion: An Accurate Method for\\xa0Higher-Resolution Image Generation", Computer Vision – ECCV 2024, vol.15064, pp.38, 2025.
