Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Results generated by the SDXL with our approach UltraStyle.

Reprinted from [http://xhslink.com/o/nfgAm1FZ5w] under a CC BY license, with permission from Xiaoming Huang, original copyright 2024. Reprinted from [https://pan.baidu.com/s/10_CjlBAaXZ6vB_RONzfU3g?pwd=b97i] under a CC BY license, with permission from Yi Yang, original copyright 2025.

More »

Fig 1 Expand

Fig 2.

Overview of our UltraStyle.

To facilitate the training of both style and content LoRA modules, we replace the conventional prediction paradigm with a novel prediction formulation. For content LoRA training, we design a loss transition mechanism that simultaneously captures the global structural layout and the fine-grained local details of the content image. To effectively disentangle the style and content information encoded in the style image, we adopt a two-stage training framework: first, we optimize a content-consistent LoRA module via the proposed loss transition; subsequently, we freeze the content LoRA and train a dedicated style LoRA to encode stylistic variations independently. Reprinted from [https://pan.baidu.com/s/10_CjlBAaXZ6vB_RONzfU3g?pwd=b97i] under a CC BY license, with permission from Yi Yang, original copyright 2025.

More »

Fig 2 Expand

Fig 3.

We present style transfer results of our method and three baseline methods.

Reprinted from [https://pan.baidu.com/s/10_CjlBAaXZ6vB_RONzfU3g?pwd=b97i] under a CC BY license, with permission from Yi Yang, original copyright 2025. Reprinted from [http://xhslink.com/o/9GlJdtObddi] under a CC BY license, with permission from Wuwei Zhang, original copyright 2025. Reprinted from [http://xhslink.com/o/54Eeo1PlMG] under a CC BY license, with permission from Tao Pu, original copyright 2025.

More »

Fig 3 Expand

Table 1.

Quantitative comparison of style and content alignment. Lower DS and higher CLIP/DINO indicate better performance.

More »

Table 1 Expand

Fig 4.

Visualization Results of the Ablation Study.

Reprinted from [https://pan.baidu.com/s/10_CjlBAaXZ6vB_RONzfU3g?pwd=b97i] under a CC BY license, with permission from Yi Yang, original copyright 2025. Reprinted from [http://xhslink.com/o/9GlJdtObddi] under a CC BY license, with permission from Wuwei Zhang, original copyright 2025.

More »

Fig 4 Expand

Table 2.

Ablation study on the dual-phase training strategy.

More »

Table 2 Expand

Table 3.

Ablation study on the progressive loss transition strategy.

More »

Table 3 Expand

Table 4.

Ablation study on the Decoupled Inference Controller.

More »

Table 4 Expand

Fig 5.

Visualization Results of Different .

Reprinted from [https://pan.baidu.com/s/10_CjlBAaXZ6vB_RONzfU3g?pwd=b97i] under a CC BY license, with permission from Yi Yang, original copyright 2025.

More »

Fig 5 Expand