Evaluating the FLUX.1 Synthetic Data on YOLOv9 for AI-Powered Poultry Farming
Source abstract
Abstract
This research explores the role of synthetic data in enhancing the accuracy of deep learning models for automated poultry farm management. A hybrid dataset was created by combining real images of chickens with 400 FLUX.1 [dev] generated synthetic images, aiming to reduce reliance on extensive manual data collection. The YOLOv9 model was trained on various dataset compositions to assess the impact of synthetic data on detection performance. Additionally, automated annotation techniques utilizing Grounding DINO and SAM2 streamlined dataset labeling, significantly reducing manual effort. Experimental results demonstrate that models trained on a balanced combination of real and synthetic images performed comparably to those trained on larger, augmented datasets, confirming the effectiveness of synthetic data in improving model generalization. The best-performing model trained on 300 real and 100 synthetic images achieved mAP = 0.829, while models trained on 100 real and 300 synthetic images reached mAP = 0.820, highlighting the potential of generative AI to bridge data scarcity gaps in precision poultry farming. This study demonstrates that synthetic data can enhance AI-driven poultry monitoring and reduce the importance of collecting real data.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Smart Agriculture and AI · Agricultural Systems and Practices · Food Supply Chain Traceability
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Faculty for Information Systems and Technologies, University of Donja Gorica, Oktoih 1, 81000 Podgorica, Montenegro
DunavNET, Bul. Oslobodjenja 133/2, 21000 Novi Sad, Serbia
Funding
IPA II program, CFCU/MNE/213 · European High-Performance Computing Joint Undertaking (JU)
References (68)
Show source-provided references
1. USDA (2025, February 25). Livestock and Poultry: World Markets and Trade, United States Department of Agriculture, Foreign Agriculture Service. 8 April 2022, Available online: https://www.fas.usda.gov/data/livestock-and-poultry-world-markets-and-trade.
2. Internet of Things and Machine Learning Techniques in Poultry Health and Welfare Management: A Systematic Literature Review10.1016/j.compag.2022.107266 ↗
3. FAO (2018). The Future of Food and Agriculture: Alternative Pathways to 2050, Food and Agriculture Organization of the United Nations.
4. Cakic, S., Popovic, T., Krco, S., Nedic, D., Babic, D., and Jovovic, I. (2023). Developing Edge AI Computer Vision for Smart Poultry Farms Using Deep Learning and HPC. Sensors, 23.10.3390/s23063002 ↗
5. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27–30). You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.91 ↗
6. Ren, S., He, K., Girshick, R., and Sun, J. (2014, January 8–13). Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. Proceedings of the 28th International Conference on Neural Information Processing Systems, Cambridge, MA, USA.
7. He, K., Gkioxari, G., Dollár, P., and Girshick, R. (2017, January 22–29). Mask R-CNN. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.322 ↗
8. Rabbani, A., and Hussain, M. (2024). YOLOv1 to YOLOv10: A Comprehensive Review of YOLO Variants and Their Application in the Agricultural. arXiv.
9. Analysis of the Performance of Faster R-CNN and YOLOv8 in Detecting Fishing Vessels and Fishes in Real Time10.7717/peerj-cs.2033 ↗
10. Comparing YOLOv8 and Mask R-CNN for Instance Segmentation in Complex Orchard Environments
11. Camacho, J., and Morocho-Cayamcela, M.E. (2023). Mask R-CNN and YOLOv8 Comparison to Perform Tomato Maturity Recognition. Communications in Computer and Information Science, Springer.10.1007/978-3-031-45438-7_26 ↗
12. Alif, M., and Hussain, M. (2025). YOLOv12: A Breakdown of the Key Architectural Features. arXiv.
13. Geetha, A.S., and Hussain, M. (2024). A Comparative Analysis of YOLOv5, YOLOv8, and YOLOv10 in Kitchen Safety. arXiv.
14. Ultralytics (2025, February 27). YOLOv11 Overview. Available online: https://docs.ultralytics.com/models/yolo11/#overview.
15. Liu, J., Zhou, Y., Li, Y., Li, Y., Hong, S., Li, Q., Liu, X., Lu, M., and Wang, X. (2023, January 26–27). Exploring the Integration of Digital Twin and Generative AI in Agriculture. Proceedings of the 15th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC), Hangzhou, China.10.1109/IHMSC58761.2023.00059 ↗
16. Klair, Y.S., Agrawal, K., and Kumar, A. (2024, January 15–16). Impact of Generative AI in Diagnosing Diseases in Agriculture. Proceedings of the 2nd International Conference on Disruptive Technologies (ICDT), Greater Noida, India.10.1109/ICDT61202.2024.10489759 ↗
17. Productivity Improvement with Generative AI Framework for Data Enrichment in Agriculture10.17762/ijritcc.v11i9.8859 ↗
18. Majumder, S., Khandelwal, Y., and Sornalakshmi, K. (2024, January 2–4). Computer Vision and Generative AI for Yield Prediction in Digital Agriculture. Proceedings of the 2nd International Conference on Networking and Communications (ICNWC), Chennai, India.10.1109/ICNWC60771.2024.10537337 ↗
19. Yang, Z. (2025, February 25). The Ultimate FLUX.1 Hands-On Guide. Available online: https://medium.com/@researchgraph/the-ultimate-flux-1-hands-on-guide-067fc053fedd.
20. Lei, J., Zhang, R., Hu, X., Lin, W., Li, Z., Sun, W., Du, R., Zhuo, L., Li, Z., and Li, X. (2025). IMAGINE-E: Image Generation Intelligence Evaluation of State-of-the-art Text-to-Image Models. arXiv.
21. Oñoro-Rubio, D., and López-Sastre, R.J. (2016). Towards Perspective-Free Object Counting with Deep Learning. Computer Vision—ECCV 2016, Springer.10.1007/978-3-319-46478-7_38 ↗
22. Laradji, I.H., Rostamzadeh, N., Pinheiro, P.O., Vazquez, D., and Schmidt, M. (2018). Where Are the Blobs: Counting by Localization with Point Supervision. Computer Vision—ECCV 2018, Springer.10.1007/978-3-030-01216-8_34 ↗
23. Automated pig counting using deep learning10.1016/j.compag.2019.05.049 ↗
24. Automated cattle counting using mask R-CNN in Quadcopter Vision System10.1016/j.compag.2020.105300 ↗
25. Cao, L., Xiao, Z., Liao, X., Yao, Y., Wu, K., Mu, J., Li, J., and Pu, H. (2021). Automated Chicken Counting in Surveillance Camera Environments Based on the Point Supervision Algorithm: LC-DenseFCN. Agriculture, 11.10.3390/agriculture11060493 ↗
26. Automated Individual Pig Localisation, Tracking and Behaviour Metric Extraction Using Deep Learning10.1109/ACCESS.2019.2933060 ↗
27. Automatic Monitoring of Chicken Movement and Drinking Time Using Convolutional Neural Networks10.13031/trans.13607 ↗
28. ChickTrack—A quantitative tracking tool for measuring chicken activity10.1016/j.measurement.2022.110819 ↗
29. Liu, H.-W., Chen, C.-H., Tsai, Y.-C., Hsieh, K.-W., and Lin, H.-T. (2021). Identifying Images of Dead Chickens with a Chicken Removal System Integrated with a Deep Learning Algorithm. Sensors, 21.10.3390/s21113579 ↗
30. Elmessery, W.M., Gutiérrez, J., Abd El-Wahhab, G.G., Elkhaiat, I.A., El-Soaly, I.S., Alhag, S.K., Al-Shuraym, L.A., Akela, M.A., Moghanm, F.S., and Abdelshafie, M.F. (2023). YOLO-Based Model for Automatic Detection of Broiler Pathological Phenomena through Visual and Thermal Images in Intensive Poultry Houses. Agriculture, 13.10.3390/agriculture13081527 ↗
31. Li, G., Hui, X., Lin, F., and Zhao, Y. (2020). Developing and Evaluating Poultry Preening Behavior Detectors via Mask R-CNN. Animals, 10.10.3390/ani10101762 ↗
32. Monitoring Activity Index and Behaviors of Cage-Free Hens with Advanced Deep Learning Technologies10.1016/j.psj.2024.104193 ↗
33. Ma, X., Lu, X., Huang, Y., Yang, X., Xu, Z., Mo, G., Ren, Y., and Li, L. (2022). An Advanced Chicken Face Detection Network Based on GAN and MAE. Animals, 12.10.3390/ani12213055 ↗
34. Broiler Stunned State Detection Based on an Improved Fast R-CNN Algorithm10.3382/ps/pez564 ↗
35. Muhammad, A., Salman, Z., Lee, K., and Han, D. (2023). Harnessing the Power of Diffusion Models for Plant Disease Image Augmentation. Front. Plant Sci., 14.10.3389/fpls.2023.1280496 ↗
36. Generative Adversarial Networks (GANs) for Image Augmentation in Agriculture: A Systematic Review10.1016/j.compag.2022.107208 ↗
37. Goyal, M., and Mahmoud, Q.H. (2024). A Systematic Review of Synthetic Data Generation Techniques Using Generative AI. Electronics, 13.10.3390/electronics13173509 ↗
38. Klein, J., Waller, R., Pirk, S., Pałubicki, W., Tester, M., and Michels, D.L. (2024). Synthetic Data at Scale: A Development Model to Efficiently Leverage Machine Learning in Agriculture. Front. Plant Sci., 15.10.3389/fpls.2024.1360113 ↗
39. Nikolenko, S.I. (2019). Synthetic Data for Deep Learning in Computer Vision: A Survey. arXiv.
40. Seth, P., Bhandari, A., and Lakara, K. (2023). Analyzing Effects of Fake Training Data on the Performance of Deep Learning Systems. arXiv.
41. HuggingFace (2025, February 25). FLUX 1.1-dev. Available online: https://huggingface.co/black-forest-labs/FLUX.1-dev.
42. agroNET (2025, February 26). Digital Farming Management. Available online: https://digitalfarming.eu.
43. Liu, S., Zeng, Z., Ren, T., Li, F., Zhang, H., Jiang, Q., Yang, J., Li, C., Yang, J., and Su, H. (2023). Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection. arXiv.10.1007/978-3-031-72970-6_3 ↗
44. Jocher, G., Chaurasia, A., and Qiu, J. (2025, February 25). Ultralytics YOLO. Available online: https://github.com/ultralytics/ultralytics.
45. (2025, February 25). Roboflow (Version 1.0) [Software]. Available online: https://roboflow.com.
46. Replicate, Inc (2025, February 25). Replicate Platform. Available online: https://replicate.com.
47. Belekar, A. (2024, November 12). Fine-Tuning Flux.1 with Your Own Images: Top 3 Methods. Available online: https://blog.segmind.com/fine-tuning-flux-1-with-your-own-images-top-3-methods/.
48. Mullins, C.C., Esau, T.J., Zaman, Q.U., Toombs, C.L., and Hennessy, P.J. (2024). Leveraging Zero-Shot Detection Mechanisms to Accelerate Image Annotation for Machine Learning in Wild Blueberry (Vaccinium angustifolium Ait.). Agronomy, 14.10.3390/agronomy14122830 ↗
49. Ravi, N., Gabeur, V., Hu, Y.-T., Hu, R., Ryali, C., Ma, T., Khedr, H., Rädle, R., Rolland, C., and Gustafson, L. (2024). SAM 2: Segment Anything in Images and Videos. arXiv.
50. Roboflow Team (2024, November 12). Segment Anything: Roboflow Image Segmentation. Available online: https://ai.meta.com/blog/segment-anything-roboflow-image-segmentation/.
51. (2025, March 15). FLUX, Github. Available online: https://github.com/black-forest-labs/flux.
52. Yang, C., Liu, C., Deng, X., Kim, D., Mei, X., Shen, X., and Chen, L.-C. (2024). 1.58-bit FLUX: Efficient Quantization of Text-to-Image Models. arXiv.
53. (2025, February 27). Flux.1-Architecture-Diagram, Github. Available online: https://github.com/brayevalerien/Flux.1-Architecture-Diagram/tree/main.
54. Replicate, Inc (2025, February 27). Replicate Pricing. Available online: https://replicate.com/pricing.
55. ShakkerLabs (2025, February 12). FLUX.1 dev LoRA Antiblur. Available online: https://huggingface.co/Shakker-Labs/FLUX.1-dev-LoRA-AntiBlur.
56. ShakkerLabs (2025, February 12). FLUX.1 dev LoRA Add Details. Available online: https://huggingface.co/Shakker-Labs/FLUX.1-dev-LoRA-add-details.
57. Wang, C.-Y., Yeh, I.-H., and Liao, H.-Y.M. (2024). YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information. arXiv.10.1007/978-3-031-72751-1_1 ↗
58. Tishby, N., Pereira, F.C., and Bialek, W. (2000). The Information Bottleneck Method. arXiv.
59. Yaseen, M. (2024). What Is YOLOv9: An In-Depth Exploration of the Internal Features of the Next-Generation Object Detector. arXiv.
60. Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation10.1109/TCYB.2021.3095305 ↗
61. Terven, J.R., Cordova-Esparza, D.M., Ramirez-Pedraza, A., Chavez-Urbiola, E.A., and Romero-Gonzalez, J.A. (2024). Loss Functions and Metrics in Deep Learning. arXiv.
62. Lin, T.-Y., Goyal, P., Girshick, R., He, K., and Dollár, P. (2017, January 22–29). Focal Loss for Dense Object Detection. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.324 ↗
63. Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., and Savarese, S. (2019, January 15–20). Generalized Intersection over Union: A Metric and a Loss for Bounding Box Regression. Proceedings of the IEEE CVPR, Long Beach, CA, USA.10.1109/CVPR.2019.00075 ↗
64. Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., and Ren, D. (2020, January 7–8). Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression. Proceedings of the AAAI Conference on Artificial Intelligence, New York, NY, USA.10.1609/aaai.v34i07.6999 ↗
65. He, J., Erfani, S.M., Ma, X., Bailey, J., Chi, Y., and Hua, X.-S. (2021, January 6–14). Alpha-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression. Proceedings of the 35th Conference on Neural Information Processing Systems (NeurIPS), Online.
66. Focal and Efficient IOU Loss for Accurate Bounding Box Regression10.1016/j.neucom.2022.07.042 ↗
67. Huang, H.-W., Yang, C.-Y., Sun, J., Kim, P.-K., Kim, K.-J., Lee, K., Huang, C.-I., and Hwang, J.-N. (2023). Iterative Scale-Up ExpansionIoU and Deep Features Association for Multi-Object Tracking in Sports. arXiv.10.1109/WACVW60836.2024.00024 ↗
68. Gevorgyan, Z. (2022). SIoU Loss: More Powerful Learning for Bounding Box Regression. arXiv.