Fine-Tuning Visual Autoregressive Models for Subject-Driven Generation
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_ | 1866912510072848384 |
|---|---|
| author | Chung, Jiwoo Hyun, Sangeek Kim, Hyunjun Koh, Eunseo Lee, MinKyu Heo, Jae-Pil |
| author_facet | Chung, Jiwoo Hyun, Sangeek Kim, Hyunjun Koh, Eunseo Lee, MinKyu Heo, Jae-Pil |
| contents | Recent advances in text-to-image generative models have enabled numerous practical applications, including subject-driven generation, which fine-tunes pretrained models to capture subject semantics from only a few examples. While diffusion-based models produce high-quality images, their extensive denoising steps result in significant computational overhead, limiting real-world applicability. Visual autoregressive (VAR) models, which predict next-scale tokens rather than spatially adjacent ones, offer significantly faster inference suitable for practical deployment. In this paper, we propose the first VAR-based approach for subject-driven generation. However, naive fine-tuning VAR leads to computational overhead, language drift, and reduced diversity. To address these challenges, we introduce selective layer tuning to reduce complexity and prior distillation to mitigate language drift. Additionally, we found that the early stages have a greater influence on the generation of subject than the latter stages, which merely synthesize minor details. Based on this finding, we propose scale-wise weighted tuning, which prioritizes coarser resolutions for promoting the model to focus on the subject-relevant information instead of local details. Extensive experiments validate that our method significantly outperforms diffusion-based baselines across various metrics and demonstrates its practical usage. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_02612 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Fine-Tuning Visual Autoregressive Models for Subject-Driven Generation Chung, Jiwoo Hyun, Sangeek Kim, Hyunjun Koh, Eunseo Lee, MinKyu Heo, Jae-Pil Computer Vision and Pattern Recognition Recent advances in text-to-image generative models have enabled numerous practical applications, including subject-driven generation, which fine-tunes pretrained models to capture subject semantics from only a few examples. While diffusion-based models produce high-quality images, their extensive denoising steps result in significant computational overhead, limiting real-world applicability. Visual autoregressive (VAR) models, which predict next-scale tokens rather than spatially adjacent ones, offer significantly faster inference suitable for practical deployment. In this paper, we propose the first VAR-based approach for subject-driven generation. However, naive fine-tuning VAR leads to computational overhead, language drift, and reduced diversity. To address these challenges, we introduce selective layer tuning to reduce complexity and prior distillation to mitigate language drift. Additionally, we found that the early stages have a greater influence on the generation of subject than the latter stages, which merely synthesize minor details. Based on this finding, we propose scale-wise weighted tuning, which prioritizes coarser resolutions for promoting the model to focus on the subject-relevant information instead of local details. Extensive experiments validate that our method significantly outperforms diffusion-based baselines across various metrics and demonstrates its practical usage. |
| title | Fine-Tuning Visual Autoregressive Models for Subject-Driven Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.02612 |