Recent advances in text-to-image diffusion models, particularly Stable Diffusion, have enabled the generation of highly detailed and semantically rich images. However, personalizing these models to represent novel subjects based on a few reference images remains challenging. This often leads to catastrophic forgetting, overfitting, or large computationalthis http URLpropose a two-stage pipeline that addresses these limitations by leveraging LoRA-based fine-tuning on the attention weights within the U-Net of the Stable Diffusion XL (SDXL) model. First, we use the unmodified SDXL to generate a generic scene by replacing the subject with its class label. Then, we selectively insert the personalized subject through a segmentation-driven image-to-image (Img2Img) pipeline that uses the trained LoRAthis http URLframework isolates the subject encoding from the overall composition, thus preserving SDXL's broader generative capabilities while integrating the new subject in a high-fidelity manner. Our method achieves a DINO similarity score of 0.789 on SDXL, outperforming existing personalized text-to-image approaches.
View on arXiv@article{tiwari2025_2505.10743,
title={ IMAGE-ALCHEMY: Advancing subject fidelity in personalised text-to-image generation },
author={ Amritanshu Tiwari and Cherish Puniani and Kaustubh Sharma and Ojasva Nema },
journal={arXiv preprint arXiv:2505.10743},
year={ 2025 }
}