LCGD: Enhancing Text-to-Video Generation via Contextual LLM Guidance and U-Net Denoising
IEEE Access · 2025 · 13 · 47068-47085
DOI: 10.1109/access.2025.3550945 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2025. Verfasst von Muhammad Waseem und 2 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Diffusion models have emerged as a leading solution in computer vision and they excel at audio, image, and video generation by utilizing the Markov chain to map complex latent spaces. These models outperform other generative models such as GANs and VAEs, with their noising and denoising processes modeled after U-Net architecture, enabling high-quality text-to-image and text-to-video synthesis. However, existing research has largely focused on application rather than improving underlying architectures, leading to limitations, such as oversmoothing in approaches like FreeU. To address these gaps, we introduce LLM Contextual Guided Diffusion (LCGD), which integrates large language models (LLMs) into the noising and denoising phases to enhance semantic understanding, noise modulation, and feature selection. This approach improves the output realism and coherence, as demonstrated by our results, where SD+LCGD achieved 89.91% compared to 85.88% for SD+FreeU.
Zitieren
APA
Waseem, M., Khan, M. U. G., & Khurshid, S. K. (2025). LCGD: Enhancing Text-to-Video Generation via Contextual LLM Guidance and U-Net Denoising. IEEE Access, 13, 47068-47085. https://doi.org/10.1109/access.2025.3550945
Vancouver
Waseem M, Khan MUG, Khurshid SK. LCGD: Enhancing Text-to-Video Generation via Contextual LLM Guidance and U-Net Denoising. IEEE Access. 2025;13:47068-47085. doi:10.1109/access.2025.3550945
BibTeX
@article{Waseem2025,
author = {Waseem, Muhammad and Khan, Muhammad Usman Ghani and Khurshid, Syed Khaldoon},
title = {LCGD: Enhancing Text-to-Video Generation via Contextual LLM Guidance and U-Net Denoising},
journal = {IEEE Access},
year = {2025},
volume = {13},
pages = {47068--47085},
doi = {10.1109/access.2025.3550945}
}
EUVIMED