A New Chinese Landscape Paintings Generation Model based on Stable Diffusion using DreamBooth
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916365215989760 |
|---|---|
| author | Gu, Yujia Fang, Xinyu Deng, Xueyuan Peng, Zihan Peng, Yinan |
| author_facet | Gu, Yujia Fang, Xinyu Deng, Xueyuan Peng, Zihan Peng, Yinan |
| contents | This study mainly introduces a method combining the Stable Diffusion Model (SDM) and Parameter-Efficient Fine-Tuning method for generating Chinese Landscape Paintings. This training process is accelerated by combining LoRA with pre-trained SDM and DreamBooth with pre-trained SDM, respectively. On the Chinese Landscape Paintings Internet dataset used in this paper, this study finds that SDM combined with DreamBooth exhibits superior performance, outperforming other models, including the generic pre-trained SDM and LoRA-based fine-tuning SDM. The SDM combined with DreamBooth achieves a FID of 12.75 on the dataset and outperforms all other models in terms of expert evaluation, highlighting the model's versatility in the field of Chinese Landscape Paintings given the unique identifier, high fidelity and high quality. This study illustrates the potential of specialised fine-tuning method to improve the performance of SDM on domain-specific tasks, particularly in the domain of Landscape Paintings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_08561 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A New Chinese Landscape Paintings Generation Model based on Stable Diffusion using DreamBooth Gu, Yujia Fang, Xinyu Deng, Xueyuan Peng, Zihan Peng, Yinan Computer Vision and Pattern Recognition This study mainly introduces a method combining the Stable Diffusion Model (SDM) and Parameter-Efficient Fine-Tuning method for generating Chinese Landscape Paintings. This training process is accelerated by combining LoRA with pre-trained SDM and DreamBooth with pre-trained SDM, respectively. On the Chinese Landscape Paintings Internet dataset used in this paper, this study finds that SDM combined with DreamBooth exhibits superior performance, outperforming other models, including the generic pre-trained SDM and LoRA-based fine-tuning SDM. The SDM combined with DreamBooth achieves a FID of 12.75 on the dataset and outperforms all other models in terms of expert evaluation, highlighting the model's versatility in the field of Chinese Landscape Paintings given the unique identifier, high fidelity and high quality. This study illustrates the potential of specialised fine-tuning method to improve the performance of SDM on domain-specific tasks, particularly in the domain of Landscape Paintings. |
| title | A New Chinese Landscape Paintings Generation Model based on Stable Diffusion using DreamBooth |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.08561 |