Novel framework for Zero-Shot Style Alignment in Text-to-Image generation, using minimal attention sharing and ensuring consistent style transfer without fine-tuning.
-
Updated
Apr 3, 2025 - Jupyter Notebook
Novel framework for Zero-Shot Style Alignment in Text-to-Image generation, using minimal attention sharing and ensuring consistent style transfer without fine-tuning.
Novel framework for Zero-Shot Style Alignment in Text-to-Image generation, incorporating Multi-Modal Context-Awareness and Multi-Reference Style Alignment, using minimal attention sharing, ensuring consistent style transfer without fine-tuning.
Accepted at the CVPR 2025 Workshop on AI for Creative Visual Content Generation, Editing and Understanding and published in the Official CVPR Workshop Procedings. Z-SASLM is a zero-shot framework for multi-style image synthesis leveraging Spherical Linear Interpolation (SLI) to achieve smooth, coherent blending—without any fine-tuning.
Add a description, image, and links to the style-aligned topic page so that developers can more easily learn about it.
To associate your repository with the style-aligned topic, visit your repo's landing page and select "manage topics."