IMAGE-ALCHEMY: Advancing subject fidelity in personalised text-to-image generation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916739315400704 |
|---|---|
| author | Tiwari, Amritanshu Puniani, Cherish Sharma, Kaustubh Nema, Ojasva |
| author_facet | Tiwari, Amritanshu Puniani, Cherish Sharma, Kaustubh Nema, Ojasva |
| contents | 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 computational overhead.We propose 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 LoRA weights.This framework 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_10743 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | IMAGE-ALCHEMY: Advancing subject fidelity in personalised text-to-image generation Tiwari, Amritanshu Puniani, Cherish Sharma, Kaustubh Nema, Ojasva Computer Vision and Pattern Recognition 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 computational overhead.We propose 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 LoRA weights.This framework 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. |
| title | IMAGE-ALCHEMY: Advancing subject fidelity in personalised text-to-image generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.10743 |