Diffusion Transformers (DiTs) have exhibited robust capabilities in image generation tasks. However, accurate text-guided image editing for multimodal DiTs (MM-DiTs) still poses a significant challenge. Unlike UNet-based structures that could utilize self/cross-attention maps for semantic editing, MM-DiTs inherently lack support for explicit and consistent incorporated text guidance, resulting in semantic misalignment between the edited results and texts. In this study, we disclose the sensitivity of different attention heads to different image semantics within MM-DiTs and introduce HeadRouter , a training-free image editing framework that edits the source image by adaptively routing the text guidance to different attention heads in MM-DiTs. Furthermore, we propose a dual-token refinement module to refine text/image token representations for precise semantic guidance and accurate region expression. Experiments on multiple benchmarks demonstrate HeadRouter’s performance in terms of editing fidelity and image quality. The code is available at https://github.com/ICTMCG/HeadRouter .

Despite the impressive results of arbitrary image-guided style transfer methods, text-driven image stylization has recently been proposed for transferring a natural image into a stylized one according to textual descriptions of the target style provided by the user. Unlike the previous image-to-image transfer approaches, text-guided stylization progress provides users with a more precise and intuitive way to express the desired style. However, the huge discrepancy between cross-modal inputs/outputs makes it challenging to conduct text-driven image stylization in a typical feed-forward CNN pipeline. In this article, we present DiffStyler, a dual diffusion processing architecture to control the balance between the content and style of the diffused results. The cross-modal style information can be easily integrated as guidance during the diffusion process step-by-step. Furthermore, we propose a content image-based learnable noise on which the reverse denoising process is based, enabling the stylization results to better preserve the structure information of the content image. We validate the proposed DiffStyler beyond the baseline methods through extensive qualitative and quantitative experiments. The code is available at https://github.com/haha-lisa/Diffstyler.

Personalized generation paradigms empower designers to customize visual intellectual property with the help of textual descriptions by adapting pre-trained text-to-image models on a few images. Recent studies focus on simultaneously customizing content and detailed visual style in images but often struggle with entangling the two. In this study, we reconsider the customization of content and style concepts from the perspective of parameter space construction. Unlike existing methods that utilize a shared parameter space for content and style learning, we propose a novel framework that separates the parameter space to facilitate individual learning of content and style by introducing “partly learnable projection” (PLP) matrices to separate the original adapters into divided sub-parameter spaces. A “ break-for-make ” customization learning pipeline based on PLP is proposed: we first break the original adapters into “up projection” and “down projection” for content and style concept under orthogonal prior and then make the entity parameter space by reconstructing the content and style PLP matrices by using Riemannian preconditioning to adaptively balance content and style learning. Experiments on various styles, including textures, materials, and artistic style, show that our method outperforms state-of-the-art single/multiple concept learning pipelines regarding content-style-prompt alignment. Code is available at https://github.com/ICTMCG/Break-for-make .

Although remarkable progress has been made in image style transfer, style is just one of the components of artistic paintings. Directly transferring extracted style features to natural images often results in outputs with obvious synthetic traces. This is because key painting attributes including layout, perspective, shape, and semantics often cannot be conveyed and expressed through style transfer. Large-scale pretrained text-to-image generation models have demonstrated their capability to synthesize a vast amount of high-quality images. However, even with extensive textual descriptions, it is challenging to fully express the unique visual properties and details of paintings. Moreover, generic models often disrupt the overall artistic effect when modifying specific areas, making it more complicated to achieve a unified aesthetic in artworks. Our main novel idea is to integrate multimodal semantic information as a synthesis guide into artworks, rather than transferring style to the real world. We also aim to reduce the disruption to the harmony of artworks while simplifying the guidance conditions. Specifically, we propose an innovative multi-task unified framework called CreativeSynth, based on the diffusion model with the ability to coordinate multimodal inputs. CreativeSynth combines multimodal features with customized attention mechanisms to seamlessly integrate real-world semantic content into the art domain through Cross-Art-Attention for aesthetic maintenance and semantic fusion. We demonstrate the results of our method across a wide range of different art categories, proving that CreativeSynth bridges the gap between generative models and artistic expression.

The essence of a video lies in the dynamic motions. While text-to-video generative diffusion models have made significant strides in creating diverse content, effectively controlling specific motions through text prompts remains a challenge. By utilizing user-specified reference videos, the more precise guidance for character actions, object movements, and camera movements can be achieved. This gives rise to the task of motion customization, where the primary challenge lies in effectively decoupling the appearance and motion within a video clip. To address this challenge, we introduce MotionCrafter, a novel one-shot instance-guided motion customization method that is suitable for both pre-trained text-to-video and text-to-image diffusion models. MotionCrafter employs a parallel spatial-temporal architecture that integrates the reference motion into the temporal component of the base model, while independently adjusting the spatial module for character or style control. To enhance the disentanglement of motion and appearance, we propose an innovative dual-branch motion disentanglement approach, which includes a motion disentanglement loss and an appearance prior enhancement strategy. To facilitate more efficient learning of motions, we further propose a novel timestep-layered tuning strategy that directs the diffusion model to focus on motion-level information. Through comprehensive quantitative and qualitative experiments, along with user preference tests, we demonstrate that MotionCrafter can successfully integrate dynamic motions while maintaining the coherence and quality of the base model, providing a wide range of appearance generation capabilities. MotionCrafter can be applied to various personalized backbones in the community to generate videos with a variety of artistic styles.

Despite the remarkable process in the field of arbitrary image style transfer (AST), inconsistent evaluation continues to plague style transfer research. Existing methods often suffer from limited objective evaluation and inconsistent subjective feedback, hindering reliable comparisons among AST variants. In this study, we propose a multi-granularity assessment system that combines standardized objective and subjective evaluations. We collect a fine-grained dataset considering a range of image contexts such as different scenes, object complexities, and rich parsing information from multiple sources. Objective and subjective studies are conducted using the collected dataset. Specifically, we innovate on traditional subjective studies by developing an online evaluation system utilizing a combination of point-wise, pair-wise, and group-wise questionnaires. Finally, we bridge the gap between objective and subjective evaluations by examining the consistency between the results from the two studies. We experimentally evaluate CNN-based, flow-based, transformer-based, and diffusion-based AST methods by the proposed multi-granularity assessment system, which lays the foundation for a reliable and robust evaluation. Providing standardized measures, objective data, and detailed subjective feedback empowers researchers to make informed comparisons and drive innovation in this rapidly evolving field.

With the development of diffusion models, text-guided image style transfer has demonstrated great controllable and high-quality results. However, the utilization of text for diverse music style transfer poses significant challenges, primarily due to the limited availability of matched audio-text datasets. Music, being an abstract and complex art form, exhibits variations and intricacies even within the same genre, thereby making accurate textual descriptions challenging. This paper presents a music style transfer approach that effectively captures musical attributes using minimal data. We introduce a novel time-varying textual inversion module to precisely capture mel-spectrogram features at different levels. During inference, we utilize a bias-reduced stylization technique to get stable results. Experimental results demonstrate that our method can transfer the style of specific instruments, as well as incorporate natural sounds to compose melodies. Samples and code are available at https://lsfhuihuiff.github.io/MusicTI/.

The seamless integration of music with dance movements is essential for communicating the artistic intent of a dance piece. This alignment also significantly improves the immersive quality of gaming experiences and animation productions. Although there has been remarkable advancement in creating high-fidelity music from textual descriptions, current methodologies mainly focus on modulating overall characteristics such as genre and emotional tone. They often overlook the nuanced management of temporal rhythm, which is indispensable in crafting music for dance, since it intricately aligns the musical beats with the dancers’ movements. Recognizing this gap, we propose an encoder-based textual inversion technique to augment text-to-music models with visual control, facilitating personalized music generation. Specifically, we develop dual-path rhythm-genre inversion to effectively integrate the rhythm and genre of a dance motion sequence into the textual space of a text-to-music model. Contrary to traditional textual inversion methods, which directly update text embeddings to reconstruct a single target object, our approach utilizes separate rhythm and genre encoders to obtain text embeddings for two pseudo-words, adapting to the varying rhythms and genres. We collect a new dataset called In-the-wild Dance Videos (InDV) and demonstrate that our approach outperforms state-of-the-art methods across multiple evaluation metrics. Furthermore, our method is able to adapt to changes in tempo and effectively integrates with the inherent text-guided generation capability of the pre-trained model. Our source code and demo videos are available at https://github.com/lsfhuihuiff/Dance-to-music_Siggraph_Asia_2024.

Large-scale text-to-video diffusion models have shown outstanding capabilities. However, their direct application to video stylization is hindered by the limited availability of text-to-video datasets and computational resources. Moreover, meeting content preservation standards for style transfer tasks is challenging due to the stochastic and destructive nature of the noise addition process. This letter introduces a succinct video stylization approach, named Style-A-Video, which leverages a generative pre-trained transformer and an image latent diffusion model for text-controlled video stylization. We improve the guidance conditions in the denoising process to maintain a balance between artistic expression and structural preservation. Additionally, by integrating sampling optimization and temporal consistency modules, we address inter-frame flickering and prevent additional artifacts. Comprehensive experimental results demonstrate superior content preservation and stylistic performance while minimizing resource consumption.

The artistic style within a painting is the means of expression, which includes not only the painting material, colors, and brushstrokes, but also the high-level attributes, including semantic elements and object shapes. Previous arbitrary example-guided artistic image generation methods often fail to control shape changes or convey elements. Pre-trained text-to-image synthesis diffusion probabilistic models have achieved remarkable quality but often require extensive textual descriptions to accurately portray the attributes of a particular painting. The uniqueness of an artwork lies in the fact that it cannot be adequately explained with normal language. Our key idea is to learn the artistic style directly from a single painting and then guide the synthesis without providing complex textual descriptions. Specifically, we perceive style as a learnable textual description of a painting. We propose an inversion-based style transfer method (InST), which can efficiently and accurately learn the key information of an image, thus capturing and transferring the artistic style of a painting. We demonstrate the quality and efficiency of our method on numerous paintings of various artists and styles. Codes are available at https://github.com/zyxElsa/InST.

Personalizing generative models offers a way to guide image generation with user-provided references. Current personalization methods can invert an object or concept into the textual conditioning space and compose new natural sentences for text-to-image diffusion models. However, representing and editing specific visual attributes such as material, style, and layout remains a challenge, leading to a lack of disentanglement and editability. To address this problem, we propose a novel approach that leverages the step-by-step generation process of diffusion models, which generate images from low to high frequency information, providing a new perspective on representing, generating, and editing images. We develop the Prompt Spectrum Space P*, an expanded textual conditioning space, and a new image representation method called ProSpect. ProSpect represents an image as a collection of inverted textual token embeddings encoded from per-stage prompts, where each prompt corresponds to a specific generation stage (i.e., a group of consecutive steps) of the diffusion model. Experimental results demonstrate that P* and ProSpect offer better disentanglement and controllability compared to existing methods. We apply ProSpect in various personalized attribute-aware image generation applications, such as image-guided or text-driven manipulations of materials, style, and layout, achieving previously unattainable results from a single image input without fine-tuning the diffusion models. Our source code is available at https://github.com/zyxElsa/ProSpect.

This work presents Unified Contrastive Arbitrary Style Transfer (UCAST), a novel style representation learning and transfer framework, that can fit in most existing arbitrary image style transfer models, such as CNN-based, ViT-based, and flow-based methods. As the key component in image style transfer tasks, a suitable style representation is essential to achieve satisfactory results. Existing approaches based on deep neural networks typically use second-order statistics to generate the output. However, these hand-crafted features computed from a single image cannot leverage style information sufficiently, which leads to artifacts such as local distortions and style inconsistency. To address these issues, we learn style representation directly from a large number of images based on contrastive learning by considering the relationships between specific styles and the holistic style distribution. Specifically, we present an adaptive contrastive learning scheme for style transfer by introducing an input-dependent temperature. Our framework consists of three key components: a parallel contrastive learning scheme for style representation and transfer, a domain enhancement (DE) module for effective learning of style distribution, and a generative network for style transfer. Qualitative and quantitative evaluations show the results of our approach are superior to those obtained via state-of-the-art methods. The code is available at https://github.com/zyxElsa/CAST_pytorch .