The popularization of Text-to-Image (T2I) diffusion models enables the generation of high-quality images from text descriptions. However, generating diverse customized images with reference visual attributes remains challenging. This work focuses on personalizing T2I diffusion models at a more abstract concept or category level, adapting commonalities from a set of reference images while creating new instances with sufficient variations. We introduce a solution that allows a pretrained T2I diffusion model to learn a set of soft prompts, enabling the generation of novel images by sampling prompts from the learned distribution. These prompts offer text-guided editing capabilities and additional flexibility in controlling variation and mixing between multiple distributions. We also show the adaptability of the learned prompt distribution to other tasks, such as text-to-3D. Finally we demonstrate effectiveness of our approach through quantitative analysis including automatic evaluation and human assessment. Project website: https://briannlongzhao.github.io/DreamDistribution
We propose a novel text-to-speech (TTS) framework centered around a neural transducer. Our approach divides the whole TTS pipeline into semantic-level sequence-to-sequence (seq2seq) modeling and fine-grained acoustic modeling stages, utilizing discrete semantic tokens obtained from wav2vec2.0 embeddings. For a robust and efficient alignment modeling, we employ a neural transducer named token transducer for the semantic token prediction, benefiting from its hard monotonic alignment constraints. Subsequently, a non-autoregressive (NAR) speech generator efficiently synthesizes waveforms from these semantic tokens. Additionally, a reference speech controls temporal dynamics and acoustic conditions at each stage. This decoupled framework reduces the training complexity of TTS while allowing each stage to focus on semantic and acoustic modeling. Our experimental results on zero-shot adaptive TTS demonstrate that our model surpasses the baseline in terms of speech quality and speaker similarity, both objectively and subjectively. We also delve into the inference speed and prosody control capabilities of our approach, highlighting the potential of neural transducers in TTS frameworks.
Addressing the limitations of text as a source of accurate layout representation in text-conditional diffusion models, many works incorporate additional signals to condition certain attributes within a generated image. Although successful, previous works do not account for the specific localization of said attributes extended into the three dimensional plane. In this context, we present a conditional diffusion model that integrates control over three-dimensional object placement with disentangled representations of global stylistic semantics from multiple exemplar images. Specifically, we first introduce \textit{depth disentanglement training} to leverage the relative depth of objects as an estimator, allowing the model to identify the absolute positions of unseen objects through the use of synthetic image triplets. We also introduce \textit{soft guidance}, a method for imposing global semantics onto targeted regions without the use of any additional localization cues. Our integrated framework, \textsc{Compose and Conquer (CnC)}, unifies these techniques to localize multiple conditions in a disentangled manner. We demonstrate that our approach allows perception of objects at varying depths while offering a versatile framework for composing localized objects with different global semantics. Code: https://github.com/tomtom1103/compose-and-conquer/
Recovering degraded low-resolution text images is challenging, especially for Chinese text images with complex strokes and severe degradation in real-world scenarios. Ensuring both text fidelity and style realness is crucial for high-quality text image super-resolution. Recently, diffusion models have achieved great success in natural image synthesis and restoration due to their powerful data distribution modeling abilities and data generation capabilities. In this work, we propose an Image Diffusion Model (IDM) to restore text images with realistic styles. For diffusion models, they are not only suitable for modeling realistic image distribution but also appropriate for learning text distribution. Since text prior is important to guarantee the correctness of the restored text structure according to existing arts, we also propose a Text Diffusion Model (TDM) for text recognition which can guide IDM to generate text images with correct structures. We further propose a Mixture of Multi-modality module (MoM) to make these two diffusion models cooperate with each other in all the diffusion steps. Extensive experiments on synthetic and real-world datasets demonstrate that our Diffusion-based Blind Text Image Super-Resolution (DiffTSR) can restore text images with more accurate text structures as well as more realistic appearances simultaneously.
Recently introduced ControlNet has the ability to steer the text-driven image generation process with geometric input such as human 2D pose, or edge features. While ControlNet provides control over the geometric form of the instances in the generated image, it lacks the capability to dictate the visual appearance of each instance. We present FineControlNet to provide fine control over each instance's appearance while maintaining the precise pose control capability. Specifically, we develop and demonstrate FineControlNet with geometric control via human pose images and appearance control via instance-level text prompts. The spatial alignment of instance-specific text prompts and 2D poses in latent space enables the fine control capabilities of FineControlNet. We evaluate the performance of FineControlNet with rigorous comparison against state-of-the-art pose-conditioned text-to-image diffusion models. FineControlNet achieves superior performance in generating images that follow the user-provided instance-specific text prompts and poses compared with existing methods. Project webpage: https://samsunglabs.github.io/FineControlNet-project-page
Relationships are essential to our happiness and wellbeing. The dissolution of a relationship, the final stage of relationship's lifecycle and one of the most stressful events in an individual's life, can have profound and long-lasting impacts on people. With the breakup process increasingly facilitated by computer-mediated communication (CMC), and the likely future influence of AI-mediated communication (AIMC) tools, we conducted a semi-structured interview study with 21 participants. We aim to understand: 1) the current role of technology in the breakup process, 2) the needs and support individuals have during the process, and 3) how AI might address these needs. Our research shows that people have distinct needs at various stages of ending a relationship. Presently, technology is used for information gathering and community support, acting as a catalyst for breakups, enabling ghosting and blocking, and facilitating communication. Participants anticipate that AI could aid in sense-making of their relationship leading up to the breakup, act as a mediator, assist in crafting appropriate wording, tones, and language during breakup conversations, and support companionship, reflection, recovery, and growth after a breakup. Our findings also demonstrate an overlap between the breakup process and the Transtheoretical Model (TTM) of behavior change. Through the lens of TTM, we explore the potential support and affordances AI could offer in breakups, including its benefits and the necessary precautions regarding AI's role in this sensitive process.
The explosion of visual content available online underscores the requirement for an accurate machine assessor to robustly evaluate scores across diverse types of visual contents. While recent studies have demonstrated the exceptional potentials of large multi-modality models (LMMs) on a wide range of related fields, in this work, we explore how to teach them for visual rating aligned with human opinions. Observing that human raters only learn and judge discrete text-defined levels in subjective studies, we propose to emulate this subjective process and teach LMMs with text-defined rating levels instead of scores. The proposed Q-Align achieves state-of-the-art performance on image quality assessment (IQA), image aesthetic assessment (IAA), as well as video quality assessment (VQA) tasks under the original LMM structure. With the syllabus, we further unify the three tasks into one model, termed the OneAlign. In our experiments, we demonstrate the advantage of the discrete-level-based syllabus over direct-score-based variants for LMMs. Our code and the pre-trained weights are released at https://github.com/Q-Future/Q-Align.
Class Activation Map (CAM) has emerged as a popular tool for weakly supervised semantic segmentation (WSSS), allowing the localization of object regions in an image using only image-level labels. However, existing CAM methods suffer from under-activation of target object regions and false-activation of background regions due to the fact that a lack of detailed supervision can hinder the model's ability to understand the image as a whole. In this paper, we propose a novel Question-Answer Cross-Language-Image Matching framework for WSSS (QA-CLIMS), leveraging the vision-language foundation model to maximize the text-based understanding of images and guide the generation of activation maps. First, a series of carefully designed questions are posed to the VQA (Visual Question Answering) model with Question-Answer Prompt Engineering (QAPE) to generate a corpus of both foreground target objects and backgrounds that are adaptive to query images. We then employ contrastive learning in a Region Image Text Contrastive (RITC) network to compare the obtained foreground and background regions with the generated corpus. Our approach exploits the rich textual information from the open vocabulary as additional supervision, enabling the model to generate high-quality CAMs with a more complete object region and reduce false-activation of background regions. We conduct extensive analysis to validate the proposed method and show that our approach performs state-of-the-art on both PASCAL VOC 2012 and MS COCO datasets. Code is available at: https://github.com/CVI-SZU/QA-CLIMS
In recent years, text-to-video retrieval methods based on CLIP have experienced rapid development. The primary direction of evolution is to exploit the much wider gamut of visual and textual cues to achieve alignment. Concretely, those methods with impressive performance often design a heavy fusion block for sentence (words)-video (frames) interaction, regardless of the prohibitive computation complexity. Nevertheless, these approaches are not optimal in terms of feature utilization and retrieval efficiency. To address this issue, we adopt multi-granularity visual feature learning, ensuring the model's comprehensiveness in capturing visual content features spanning from abstract to detailed levels during the training phase. To better leverage the multi-granularity features, we devise a two-stage retrieval architecture in the retrieval phase. This solution ingeniously balances the coarse and fine granularity of retrieval content. Moreover, it also strikes a harmonious equilibrium between retrieval effectiveness and efficiency. Specifically, in training phase, we design a parameter-free text-gated interaction block (TIB) for fine-grained video representation learning and embed an extra Pearson Constraint to optimize cross-modal representation learning. In retrieval phase, we use coarse-grained video representations for fast recall of top-k candidates, which are then reranked by fine-grained video representations. Extensive experiments on four benchmarks demonstrate the efficiency and effectiveness. Notably, our method achieves comparable performance with the current state-of-the-art methods while being nearly 50 times faster.
We introduce a cryptographic method to hide an arbitrary secret payload in the response of a Large Language Model (LLM). A secret key is required to extract the payload from the model's response, and without the key it is provably impossible to distinguish between the responses of the original LLM and the LLM that hides a payload. In particular, the quality of generated text is not affected by the payload. Our approach extends a recent result of Christ, Gunn and Zamir (2023) who introduced an undetectable watermarking scheme for LLMs.