StyleMaster: Towards Flexible Stylized Image Generation with Diffusion Models
Keywords: image stylization, diffusion model
Abstract: Stylized Text-to-Image Generation (STIG) aims to generate images based on text prompts and style reference images. We in this paper propose a novel framework dubbed StyleMaster for this task by leveraging pretrained Stable Diffusion (SD), which addresses previous problems such as misinterpreted style and inconsistent semantics. The enhancement lies in two novel modules: multi-source style embedder and dynamic attention adapter. In order to provide SD with better style embeddings, we propose the multi-source style embedder, which considers both global and local level visual information along with textual information, thereby offering both complementary style-related and semantic-related knowledge. Additionally, aiming for better balance between the adapter capacity and semantic control, the proposed dynamic attention adapter is applied to the diffusion UNet in which adaptation weights are dynamically calculated based on the style embeddings. Two objective functions are introduced to optimize the model alongside the denoising loss, which can further enhance semantic and style consistency. Extensive experiments demonstrate the superiority of StyleMaster over existing methods, rendering images with variable target styles while successfully maintaining the semantic information from the text prompts.
Primary Area: generative models
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 2096
Loading