PhytoSynth: Leveraging Multi-modal Generative Models for Crop Disease Data Generation with Novel Benchmarking and Prompt Engineering Approach
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908361539190784 |
|---|---|
| author | Rai, Nitin Schumann, Arnold W. Boyd, Nathan |
| author_facet | Rai, Nitin Schumann, Arnold W. Boyd, Nathan |
| contents | Collecting large-scale crop disease images in the field is labor-intensive and time-consuming. Generative models (GMs) offer an alternative by creating synthetic samples that resemble real-world images. However, existing research primarily relies on Generative Adversarial Networks (GANs)-based image-to-image translation and lack a comprehensive analysis of computational requirements in agriculture. Therefore, this research explores a multi-modal text-to-image approach for generating synthetic crop disease images and is the first to provide computational benchmarking in this context. We trained three Stable Diffusion (SD) variants-SDXL, SD3.5M (medium), and SD3.5L (large)-and fine-tuned them using Dreambooth and Low-Rank Adaptation (LoRA) fine-tuning techniques to enhance generalization. SD3.5M outperformed the others, with an average memory usage of 18 GB, power consumption of 180 W, and total energy use of 1.02 kWh/500 images (0.002 kWh per image) during inference task. Our results demonstrate SD3.5M's ability to generate 500 synthetic images from just 36 in-field samples in 1.5 hours. We recommend SD3.5M for efficient crop disease data generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_01823 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PhytoSynth: Leveraging Multi-modal Generative Models for Crop Disease Data Generation with Novel Benchmarking and Prompt Engineering Approach Rai, Nitin Schumann, Arnold W. Boyd, Nathan Computer Vision and Pattern Recognition Artificial Intelligence Emerging Technologies Collecting large-scale crop disease images in the field is labor-intensive and time-consuming. Generative models (GMs) offer an alternative by creating synthetic samples that resemble real-world images. However, existing research primarily relies on Generative Adversarial Networks (GANs)-based image-to-image translation and lack a comprehensive analysis of computational requirements in agriculture. Therefore, this research explores a multi-modal text-to-image approach for generating synthetic crop disease images and is the first to provide computational benchmarking in this context. We trained three Stable Diffusion (SD) variants-SDXL, SD3.5M (medium), and SD3.5L (large)-and fine-tuned them using Dreambooth and Low-Rank Adaptation (LoRA) fine-tuning techniques to enhance generalization. SD3.5M outperformed the others, with an average memory usage of 18 GB, power consumption of 180 W, and total energy use of 1.02 kWh/500 images (0.002 kWh per image) during inference task. Our results demonstrate SD3.5M's ability to generate 500 synthetic images from just 36 in-field samples in 1.5 hours. We recommend SD3.5M for efficient crop disease data generation. |
| title | PhytoSynth: Leveraging Multi-modal Generative Models for Crop Disease Data Generation with Novel Benchmarking and Prompt Engineering Approach |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Emerging Technologies |
| url | https://arxiv.org/abs/2505.01823 |