Infusion: Inject and attention fusion for multi concept zero-shot text-based video editing

A Khandelwal - Proceedings of the IEEE/CVF International …, 2023 - openaccess.thecvf.com
Large text-to-image diffusion models have achieved remarkable success in generating
diverse, high-quality images. Additionally, these models have been successfully leveraged …
被引用次数：9 相关文章

InFusion: Inject and Attention Fusion for Multi Concept Zero-Shot Text-based Video Editing

A Khandelwal - arXiv preprint arXiv:2308.00135, 2023 - arxiv.org
Large text-to-image diffusion models have achieved remarkable success in generating
diverse, high-quality images. Additionally, these models have been successfully leveraged …

InFusion: Inject and Attention Fusion for Multi Concept Zero Shot Text based Video Editing

A Khandelwal - arXiv e-prints, 2023 - ui.adsabs.harvard.edu
Large text-to-image diffusion models have achieved remarkable success in generating
diverse high-quality images in alignment with text prompt used for editing the input image …

InFusion: Inject and Attention Fusion for Multi Concept Zero-Shot Text-based Video Editing

A Khandelwal - 2023 IEEE/CVF International Conference on …, 2023 - ieeexplore.ieee.org
Large text-to-image diffusion models have achieved remarkable success in generating
diverse, high-quality images. Additionally, these models have been successfully leveraged …

InFusion: Inject and Attention Fusion for Multi Concept Zero-Shot Text-based Video Editing

A Khandelwal - 2023 IEEE/CVF International Conference on …, 2023 - computer.org
Large text-to-image diffusion models have achieved remarkable success in generating
diverse, high-quality images. Additionally, these models have been successfully leveraged …