The synthesis of high-quality images has become a cornerstone of
advancements in generative modeling, with diffusion models emerging
as a prominent method due to their ability to produce detailed and
realistic visuals. However, achieving high fidelity often demands
extensive computational resources and prolonged training durations,
posing significant challenges in balancing model complexity with
training efficiency. Traditional methods struggle to optimize both
quality and efficiency, leaving room for innovation in design and
implementation. To address this challenge, a novel diffusion-based
framework is proposed that incorporates a hybrid noise scheduling
mechanism and adaptive model scaling. The method uses an optimized
U-Net architecture augmented with attention mechanisms to ensure
high-resolution feature capture while reducing computational
overhead. Furthermore, a diffusion-based training approach gradually
increases model complexity, enabling faster convergence and improved
efficiency. Experimental results demonstrate the efficacy of the
proposed framework. On the CelebA-HQ dataset, it achieves a Fréchet
Inception Distance (FID) score of 5.2, outperforming state-of-art
diffusion models with a 15% reduction in training time. When tested
on the CIFAR-10 dataset, the framework produces an FID score of 2.8,
marking a significant improvement over existing benchmarks. These
results highlight the model’s ability to maintain high image quality
while substantially reducing computational costs, making it feasible for
resource-constrained environments. The proposed approach bridges
the gap between computational efficiency and image synthesis quality,
paving the way for broader applications in industries such as gaming,
design, and content generation, where high-quality visuals are critical.
S. Vadhana Kumari1, Shano Maria Selvan2, S. Brilly Sangeetha3, Adeline Sneha4
Vimal Jyothi Engineering College, India1, University of Manchester, United Kingdom2, IES College of Engineering, India3, Asia Pacific University of Technology and Innovation, Malaysia4
Diffusion Models, Image Synthesis, Training Efficiency, Model Complexity, Fréchet Inception Distance
| January | February | March | April | May | June | July | August | September | October | November | December |
| 8 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
| Published By :
ICTACT
Published In :
ICTACT Journal on Soft Computing
( Volume: 15 , Issue: 3 , Pages: 3625 - 3633 )
Date of Publication :
January 2025
Page Views :
130
Full Text Views :
9
|