Hasil untuk "Style. Composition. Rhetoric"

Thierry Herman

Sara Gambella

Negli ultimi decenni, il romanzo di famiglia ha assunto un ruolo centrale nella narrativa italiana iper-contemporanea, evolvendosi attraverso un costante dialogo con altri generi e modalità narrative. Questo studio si propone di esaminare La più amata (2017) di Teresa Ciabatti e Niente di vero (2022) di Veronica Raimo, due romanzi rappresentativi di questa trasformazione, soffermandosi sulla loro intersezione con l’autofiction e il romanzo di formazione. Attraverso una prospettiva comparatistica, l’articolo esplora le strategie di rappresentazione dell’identità familiare, la tensione tra realtà e finzione, la frammentarietà della narrazione e la sovversione della linearità del percorso di formazione di un personaggio. Il family novel italiano iper-contemporaneo si configura così non solo come un luogo di riflessione critica sui legami identitari e genealogici, ma anche come un terreno di sperimentazione letteraria, attraverso il quale indagare la commistione tra i generi e la fluidità dei loro confini. 

Seyed Hadi Seyed, Ayberk Cansever, David Hart

Artistic style transfer has long been possible with the advancements of convolution- and transformer-based neural networks. Most algorithms apply the artistic style transfer to the whole image, but individual users may only need to apply a style transfer to a specific region in the image. The standard practice is to simply mask the image after the stylization. This work shows that this approach tends to improperly capture the style features in the region of interest. We propose a partial-convolution-based style transfer network that accurately applies the style features exclusively to the region of interest. Additionally, we present network-internal blending techniques that account for imperfections in the region selection. We show that this visually and quantitatively improves stylization using examples from the SA-1B dataset. Code is publicly available at https://github.com/davidmhart/StyleTransferMasked.

Ye Wang, Ruiqi Liu, Jiang Lin et al.

In this paper, we introduce OmniStyle-1M, a large-scale paired style transfer dataset comprising over one million content-style-stylized image triplets across 1,000 diverse style categories, each enhanced with textual descriptions and instruction prompts. We show that OmniStyle-1M can not only enable efficient and scalable of style transfer models through supervised training but also facilitate precise control over target stylization. Especially, to ensure the quality of the dataset, we introduce OmniFilter, a comprehensive style transfer quality assessment framework, which filters high-quality triplets based on content preservation, style consistency, and aesthetic appeal. Building upon this foundation, we propose OmniStyle, a framework based on the Diffusion Transformer (DiT) architecture designed for high-quality and efficient style transfer. This framework supports both instruction-guided and image-guided style transfer, generating high resolution outputs with exceptional detail. Extensive qualitative and quantitative evaluations demonstrate OmniStyle's superior performance compared to existing approaches, highlighting its efficiency and versatility. OmniStyle-1M and its accompanying methodologies provide a significant contribution to advancing high-quality style transfer, offering a valuable resource for the research community.

Lei Chen, Hao Li, Yuxin Zhang et al.

Text-driven image style transfer has seen remarkable progress with methods leveraging cross-modal embeddings for fast, high-quality stylization. However, most existing pipelines assume a \emph{single} textual style prompt, limiting the range of artistic control and expressiveness. In this paper, we propose a novel \emph{multi-prompt style interpolation} framework that extends the recently introduced \textbf{StyleMamba} approach. Our method supports blending or interpolating among multiple textual prompts (eg, ``cubism,'' ``impressionism,'' and ``cartoon''), allowing the creation of nuanced or hybrid artistic styles within a \emph{single} image. We introduce a \textit{Multi-Prompt Embedding Mixer} combined with \textit{Adaptive Blending Weights} to enable fine-grained control over the spatial and semantic influence of each style. Further, we propose a \emph{Hierarchical Masked Directional Loss} to refine region-specific style consistency. Experiments and user studies confirm our approach outperforms single-prompt baselines and naive linear combinations of styles, achieving superior style fidelity, text-image alignment, and artistic flexibility, all while maintaining the computational efficiency offered by the state-space formulation.

Zhanjie Zhang, Ao Ma, Ke Cao et al.

Ultra-high quality artistic style transfer refers to repainting an ultra-high quality content image using the style information learned from the style image. Existing artistic style transfer methods can be categorized into style reconstruction-based and content-style disentanglement-based style transfer approaches. Although these methods can generate some artistic stylized images, they still exhibit obvious artifacts and disharmonious patterns, which hinder their ability to produce ultra-high quality artistic stylized images. To address these issues, we propose a novel artistic image style transfer method, U-StyDiT, which is built on transformer-based diffusion (DiT) and learns content-style disentanglement, generating ultra-high quality artistic stylized images. Specifically, we first design a Multi-view Style Modulator (MSM) to learn style information from a style image from local and global perspectives, conditioning U-StyDiT to generate stylized images with the learned style information. Then, we introduce a StyDiT Block to learn content and style conditions simultaneously from a style image. Additionally, we propose an ultra-high quality artistic image dataset, Aes4M, comprising 10 categories, each containing 400,000 style images. This dataset effectively solves the problem that the existing style transfer methods cannot produce high-quality artistic stylized images due to the size of the dataset and the quality of the images in the dataset. Finally, the extensive qualitative and quantitative experiments validate that our U-StyDiT can create higher quality stylized images compared to state-of-the-art artistic style transfer methods. To our knowledge, our proposed method is the first to address the generation of ultra-high quality stylized images using transformer-based diffusion.

Lester Phillip Violeta, Wen-Chin Huang, Tomoki Toda

We propose Serenade, a novel framework for the singing style conversion (SSC) task. Although singer identity conversion has made great strides in the previous years, converting the singing style of a singer has been an unexplored research area. We find three main challenges in SSC: modeling the target style, disentangling source style, and retaining the source melody. To model the target singing style, we use an audio infilling task by predicting a masked segment of the target mel-spectrogram with a flow-matching model using the complement of the masked target mel-spectrogram along with disentangled acoustic features. On the other hand, to disentangle the source singing style, we use a cyclic training approach, where we use synthetic converted samples as source inputs and reconstruct the original source mel-spectrogram as a target. Finally, to retain the source melody better, we investigate a post-processing module using a source-filter-based vocoder and resynthesize the converted waveforms using the original F0 patterns. Our results showed that the Serenade framework can handle generalized SSC tasks with the best overall similarity score, especially in modeling breathy and mixed singing styles. We also found that resynthesizing with the original F0 patterns alleviated out-of-tune singing and improved naturalness, but found a slight tradeoff in similarity due to not changing the F0 patterns into the target style.

Nataniel Ruiz, Yuanzhen Li, Neal Wadhwa et al.

We present Magic Insert, a method for dragging-and-dropping subjects from a user-provided image into a target image of a different style in a physically plausible manner while matching the style of the target image. This work formalizes the problem of style-aware drag-and-drop and presents a method for tackling it by addressing two sub-problems: style-aware personalization and realistic object insertion in stylized images. For style-aware personalization, our method first fine-tunes a pretrained text-to-image diffusion model using LoRA and learned text tokens on the subject image, and then infuses it with a CLIP representation of the target style. For object insertion, we use Bootstrapped Domain Adaption to adapt a domain-specific photorealistic object insertion model to the domain of diverse artistic styles. Overall, the method significantly outperforms traditional approaches such as inpainting. Finally, we present a dataset, SubjectPlop, to facilitate evaluation and future progress in this area. Project page: https://magicinsert.github.io/

Xintao Jiang, Yaosen Chen, Siqin Zhang et al.

Video color style transfer aims to transform the color style of an original video by using a reference style image. Most existing methods employ neural networks, which come with challenges like opaque transfer processes and limited user control over the outcomes. Typically, users cannot fine-tune the resulting images or videos. To tackle this issue, we introduce a method that predicts specific parameters for color style transfer using two images. Initially, we train a neural network to learn the corresponding color adjustment parameters. When applying style transfer to a video, we fine-tune the network with key frames from the video and the chosen style image, generating precise transformation parameters. These are then applied to convert the color style of both images and videos. Our experimental results demonstrate that our algorithm surpasses current methods in color style transfer quality. Moreover, each parameter in our method has a specific, interpretable meaning, enabling users to understand the color style transfer process and allowing them to perform manual fine-tuning if desired.

Sahil Jain, Avik Kuthiala, Prabhdeep Singh Sethi et al.

Recent advancements in radiance fields have opened new avenues for creating high-quality 3D assets and scenes. Style transfer can enhance these 3D assets with diverse artistic styles, transforming creative expression. However, existing techniques are often slow or unable to localize style transfer to specific objects. We introduce StyleSplat, a lightweight method for stylizing 3D objects in scenes represented by 3D Gaussians from reference style images. Our approach first learns a photorealistic representation of the scene using 3D Gaussian splatting while jointly segmenting individual 3D objects. We then use a nearest-neighbor feature matching loss to finetune the Gaussians of the selected objects, aligning their spherical harmonic coefficients with the style image to ensure consistency and visual appeal. StyleSplat allows for quick, customizable style transfer and localized stylization of multiple objects within a scene, each with a different style. We demonstrate its effectiveness across various 3D scenes and styles, showcasing enhanced control and customization in 3D creation.

Ajay Patel, Jiacheng Zhu, Justin Qiu et al.

Style representations aim to embed texts with similar writing styles closely and texts with different styles far apart, regardless of content. However, the contrastive triplets often used for training these representations may vary in both style and content, leading to potential content leakage in the representations. We introduce StyleDistance, a novel approach to training stronger content-independent style embeddings. We use a large language model to create a synthetic dataset of near-exact paraphrases with controlled style variations, and produce positive and negative examples across 40 distinct style features for precise contrastive learning. We assess the quality of our synthetic data and embeddings through human and automatic evaluations. StyleDistance enhances the content-independence of style embeddings, which generalize to real-world benchmarks and outperform leading style representations in downstream applications. Our model can be found at https://huggingface.co/StyleDistance/styledistance .

Qingju Liu, Hyeongwoo Kim, Gaurav Bharaj

Audio-driven 3D facial animation has several virtual humans applications for content creation and editing. While several existing methods provide solutions for speech-driven animation, precise control over content (what) and style (how) of the final performance is still challenging. We propose a novel approach that takes as input an audio, and the corresponding text to extract temporally-aligned content and disentangled style representations, in order to provide controls over 3D facial animation. Our method is trained in two stages, that evolves from audio prominent styles (how it sounds) to visual prominent styles (how it looks). We leverage a high-resource audio dataset in stage I to learn styles that control speech generation in a self-supervised learning framework, and then fine-tune this model with low-resource audio/3D mesh pairs in stage II to control 3D vertex generation. We employ a non-autoregressive seq2seq formulation to model sentence-level dependencies, and better mouth articulations. Our method provides flexibility that the style of a reference audio and the content of a source audio can be combined to enable audio style transfer. Similarly, the content can be modified, e.g. muting or swapping words, that enables style-preserving content editing.

Guanghou Liu, Yongmao Zhang, Yi Lei et al.

Style transfer TTS has shown impressive performance in recent years. However, style control is often restricted to systems built on expressive speech recordings with discrete style categories. In practical situations, users may be interested in transferring style by typing text descriptions of desired styles, without the reference speech in the target style. The text-guided content generation techniques have drawn wide attention recently. In this work, we explore the possibility of controllable style transfer with natural language descriptions. To this end, we propose PromptStyle, a text prompt-guided cross-speaker style transfer system. Specifically, PromptStyle consists of an improved VITS and a cross-modal style encoder. The cross-modal style encoder constructs a shared space of stylistic and semantic representation through a two-stage training process. Experiments show that PromptStyle can achieve proper style transfer with text prompts while maintaining relatively high stability and speaker similarity. Audio samples are available in our demo page.

Zhizhong Wang, Lei Zhao, Wei Xing

Content and style (C-S) disentanglement is a fundamental problem and critical challenge of style transfer. Existing approaches based on explicit definitions (e.g., Gram matrix) or implicit learning (e.g., GANs) are neither interpretable nor easy to control, resulting in entangled representations and less satisfying results. In this paper, we propose a new C-S disentangled framework for style transfer without using previous assumptions. The key insight is to explicitly extract the content information and implicitly learn the complementary style information, yielding interpretable and controllable C-S disentanglement and style transfer. A simple yet effective CLIP-based style disentanglement loss coordinated with a style reconstruction prior is introduced to disentangle C-S in the CLIP image space. By further leveraging the powerful style removal and generative ability of diffusion models, our framework achieves superior results than state of the art and flexible C-S disentanglement and trade-off control. Our work provides new insights into the C-S disentanglement in style transfer and demonstrates the potential of diffusion models for learning well-disentangled C-S characteristics.

John Purfield

Abstract The climate change crisis is a matter of increasing concern to rhetoric and composition. Some scholars in the discipline, specifically on the new materialist turn, have engaged and accounted for the damage through methodologies of ontological entanglement and relationality. The potential of ontological accounts to facilitate global activism faces the obstacle of scalar derangement. By acting as Foucauldian specific intellectuals, rhetoric and composition scholars may employ new materialist ontological projects to bridge the gap between local accounts of climatological damage and a global, pluralist assemblage of climate activists.

Covadonga Valdaliso Casanova, Carmen Benítez Guerrero, Ricardo Pichel et al.

En los últimos siglos de la Edad Media se multiplicó la actividad de los llamados ‘escribanos historiadores’, profesionales de la escritura que desempeñaron labores historiográficas. Este trabajo presenta un ejemplo de ello: una lista de anales que cuenta además con la particularidad de entrelazar la historia general con informaciones de tipo local y familiar, y aporta datos para inferir el nombre de su autor.

Stefano Calabrese, Valentina Conti, Ludovica Broglia

Le recenti acquisizioni neuroscientifiche e la loro applicazione in ambito estetico e narratologico offrono un’ulteriore spiegazione alla massiccia diffusione delle immagini avvenuta negli ultimi decenni anche a livello narrativo e ci permettono di comprendere ancora più a fondo il motivo e il modo in cui veniamo catturati dalle rappresentazioni iconiche: esse attivano meccanismi di simulazione incarnata (embodied simulation) delle azioni, delle emozioni e delle sensazioni corporee in esse raffigurate, garantendo un’esperienza immersiva più ‘diretta’, rispetto alla sola lettura di un testo verbale. Il visual storytelling è pertanto considerato una tipologia narrativa proto-adamitica rispetto a quella verbale, in quanto rappresenta una dotazione biologica e cognitiva disponibile all’uomo per trasmettere concetti in maniera semplificata o più emozionalmente attraente; di contro, è provato che quando leggiamo un testo trasformiamo in immagini i concetti, esattamente come accade nelle metafore. Esistono diversi studi sperimentali che mostrano le potenzialità del visual storytelling per lo sviluppo di alcune capacità, in particolare competenza inferenziale-predittiva-esplicativa; pensiero critico; empatia e transportation; pensiero sequenziale; etichettatura di frames e scripts; memoria e apprendimento.

Carole Delaitre 

This article analyzes the representation of mass tourism in two novels by Michel Houellebecq – Lanzarote (2000) and Plateforme (2001) – and reveals that behind the apparent fascination of the protagonists for the discourses of tourism lies an unapologetic criticism of the tourist industry. In this article, I focus on the protagonists’ attacks on two types of tourist discourses (tourist guides and travel brochures) and demonstrate that while they recognize their seductive power on the consumer, they also mock their formulaic and often deceptive rhetoric by using irony, playing with stereotypes, and by quoting, parodying, and pastiching their style. Ultimately, they denounce the way in which the tourist’s experience is conditioned by a number of narratives on the country and its inhabitants that act as filters between the traveler and reality, and contribute to propagate a stereotypical and/or ideological vision of the world.

Hendrik T. Spanke, Jaime Agudo-Canalejo, Daniel Tran et al.

Lipid membranes form the barrier between the inside and outside of cells and many of their subcompartments. As such, they bind to a wide variety of nano- and micrometer sized objects and, in the presence of strong adhesive forces, strongly deform and envelop particles. This wrapping plays a key role in many healthy and disease-related processes. So far, little work has focused on the dynamics of the wrapping process. Here, using a model system of micron-sized colloidal particles and giant unilamellar lipid vesicles with tunable adhesive forces, we measure the velocity of the particle during its wrapping process as well as the forces exerted on it by the lipid membrane. Dissipation at the contact line appears to be the main factor determining the wrapping velocity and time to wrap an object.

Alba Sicher, Rabea Ganz, Andreas Menzel et al.

Structural colors are produced by wavelength-dependent scattering of light from nanostructures. While living organisms often exploit phase separation to directly assemble structurally colored materials from macromolecules, synthetic structural colors are typically produced in a two-step process involving the sequential synthesis and assembly of building blocks. Phase separation is attractive for its simplicity, but applications are limited due to a lack of robust methods for its control. A central challenge is to arrest phase separation at the desired length scale. Here, we show that solid-state polymerization-induced phase separation can produce stable structures at optical length scales. In this process, a polymeric solid is swollen and softened with a second monomer. During its polymerization, the two polymers become immiscible and phase separate. As free monomer is depleted, the host matrix resolidifies and arrests coarsening. The resulting PS-PMMA composites have a blue or white appearance. We compare these biomimetic nanostructures to those in structurally-colored feather barbs, and demonstrate the flexibility of this approach by producing structural color in filaments and large sheets.