We introduce Z-SASLM, a Zero-Shot Style-Aligned SLI (Spherical Linear Interpolation) Blending Latent Manipulation pipeline that overcomes the limitations of current blending methods. Conventional approaches rely on linear blending, assuming a flat latent space leading to suboptimal results when integrating multiple reference styles. In contrast, our framework leverages the non-linear geometry of the latent space by using SLI Blending to combine weighted style representations. By interpolating along the geodesic on the hypersphere, Z-SASLM preserves the intrinsic structure of the latent space, ensuring high-fidelity and coherent blending of diverse styles—all without the need for fine-tuning. We further propose a new metric, Weighted Multi-Style DINO VIT-B/8, designed to quantitatively evaluate the consistency of the blended styles. While our primary focus is on the theoretical and practical advantages of SLI Blending for style manipulation, we also demonstrate its effectiveness in a multi-modal content fusion setting through comprehensive experimental studies. Experimental results show that Z-SASLM achieves enhanced and robust style alignment.

Our framework is built as a modular pipeline that efficiently combines diverse style references and multi-modal cues without fine-tuning. The architecture comprises four main components:

1. Reference Image Encoding & Blending:
   • A Variational Autoencoder (VAE) extracts latent representations from each reference style image.
   • Our novel Spherical Linear Interpolation (SLI) Blending module then fuses these latent codes along the geodesic of the hypersphere, ensuring smooth and coherent style transitions.
2. Text Encoding:
   • Textual prompts are encoded using a CLIP-based module, capturing semantic cues and aligning them with visual features.
   • This stage supports both simple captions and richer prompts derived from multiple modalities.
3. Style-Aligned Image Generation:
   • The blended style representation is combined with the text embeddings to condition a diffusion-based generation process.
   • A style-aligned attention mechanism reinforces consistent style propagation throughout the image generation.
4. Optional Multi-Modal Content Fusion:
   • Additional inputs such as audio, music, or weather data are first transformed into text.
   • These are fused into a single “Multi-Content Textual Prompt” via a T5-based rephrasing module, further enriching the conditioning signal for improved creative synthesis.

• Enhanced Context: Fusing multi-modal data (e.g., image, audio, weather) enriches the textual prompt, leading to more contextually informed and creative outputs.
• Improved Style Consistency: The integration of diverse modalities boosts the robustness of style alignment across generated images.
• Comparative Advantage: Multi-modal fusion outperforms single-modal baselines in both quantitative metrics and visual quality.

• Problem of Style Dominance: Styles with higher latent activation norms (e.g., “famous” styles like Cubism) tend to dominate blending results by skewing attention scores in their favor.
• Rescaling Strategy: We identify dominant styles by checking the norm of their key vectors and apply a normalization that dampens their attention contribution while slightly boosting "normal" styles.
• Improved Balance: Experiments show that our attention rescaling technique significantly reduces the style imbalance, enabling more faithful and balanced multi-style blending.

            @misc{borgi2025zsaslmzeroshotstylealignedsli,
              title={Z-SASLM: Zero-Shot Style-Aligned SLI Blending Latent Manipulation}, 
              author={Alessio Borgi and Luca Maiano and Irene Amerini},
              year={2025},
              eprint={2503.23234},
              archivePrefix={arXiv},
              primaryClass={cs.CV},
              url={https://arxiv.org/abs/2503.23234}, 
        }