Scholarlink

<p>The use of state-of-the-art image generation models for artistic purposes on embedded devices remains challenging due to their high computational and power requirements. The goal of this research is to create a system for real-time image generation for artistic creation that integrates deep learning models with embedded hardware. The method suggested uses a diffusion-based image generation framework optimised through model pruning and TensorRT acceleration for inference on devices with limited resources. A varied dataset featuring a wide range of artistic styles was implemented to assess the visual quality and performance of the system. The experiment’s outcome shows that the system makes a Structural Similarity Index (SSIM) of 0.89 and a Fréchet Inception Distance (FID) of 16.7, while the average inference latency is 1.3&#xa0;s per image and the power consumption is around 15 W. User ratings also point out that the users have a high level of satisfaction with both the quality and promptness of the images produced. These results demonstrate the feasibility of deploying diffusion-based image generation on embedded systems under strict latency and power constraints, providing an energy-efficient and portable solution for interactive and educational generative art applications.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Research on image generation art creation assisted by deep learning and embedded systems

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月5日

查看全文
  • Yanan Niu

摘要

The use of state-of-the-art image generation models for artistic purposes on embedded devices remains challenging due to their high computational and power requirements. The goal of this research is to create a system for real-time image generation for artistic creation that integrates deep learning models with embedded hardware. The method suggested uses a diffusion-based image generation framework optimised through model pruning and TensorRT acceleration for inference on devices with limited resources. A varied dataset featuring a wide range of artistic styles was implemented to assess the visual quality and performance of the system. The experiment’s outcome shows that the system makes a Structural Similarity Index (SSIM) of 0.89 and a Fréchet Inception Distance (FID) of 16.7, while the average inference latency is 1.3 s per image and the power consumption is around 15 W. User ratings also point out that the users have a high level of satisfaction with both the quality and promptness of the images produced. These results demonstrate the feasibility of deploying diffusion-based image generation on embedded systems under strict latency and power constraints, providing an energy-efficient and portable solution for interactive and educational generative art applications.