Abstract:In this paper, we introduce ILLUME, a unified multimodal large language model (MLLM) that seamlessly integrates multimodal understanding and generation capabilities within a single large language model through a unified next-token prediction formulation. To address the large dataset size typically required for image-text alignment, we propose to enhance data efficiency through the design of a vision tokenizer that incorporates semantic information and a progressive multi-stage training procedure. This approach reduces the dataset size to just 15M for pretraining -- over four times fewer than what is typically needed -- while achieving competitive or even superior performance with existing unified MLLMs, such as Janus. Additionally, to promote synergistic enhancement between understanding and generation capabilities, which is under-explored in previous works, we introduce a novel self-enhancing multimodal alignment scheme. This scheme supervises the MLLM to self-assess the consistency between text descriptions and self-generated images, facilitating the model to interpret images more accurately and avoid unrealistic and incorrect predictions caused by misalignment in image generation. Based on extensive experiments, our proposed ILLUME stands out and competes with state-of-the-art unified MLLMs and specialized models across various benchmarks for multimodal understanding, generation, and editing.
Abstract:Despite the success of generating high-quality images given any text prompts by diffusion-based generative models, prior works directly generate the entire images, but cannot provide object-wise manipulation capability. To support wider real applications like professional graphic design and digital artistry, images are frequently created and manipulated in multiple layers to offer greater flexibility and control. Therefore in this paper, we propose a layer-collaborative diffusion model, named LayerDiff, specifically designed for text-guided, multi-layered, composable image synthesis. The composable image consists of a background layer, a set of foreground layers, and associated mask layers for each foreground element. To enable this, LayerDiff introduces a layer-based generation paradigm incorporating multiple layer-collaborative attention modules to capture inter-layer patterns. Specifically, an inter-layer attention module is designed to encourage information exchange and learning between layers, while a text-guided intra-layer attention module incorporates layer-specific prompts to direct the specific-content generation for each layer. A layer-specific prompt-enhanced module better captures detailed textual cues from the global prompt. Additionally, a self-mask guidance sampling strategy further unleashes the model's ability to generate multi-layered images. We also present a pipeline that integrates existing perceptual and generative models to produce a large dataset of high-quality, text-prompted, multi-layered images. Extensive experiments demonstrate that our LayerDiff model can generate high-quality multi-layered images with performance comparable to conventional whole-image generation methods. Moreover, LayerDiff enables a broader range of controllable generative applications, including layer-specific image editing and style transfer.
Abstract:Current large-scale diffusion models represent a giant leap forward in conditional image synthesis, capable of interpreting diverse cues like text, human poses, and edges. However, their reliance on substantial computational resources and extensive data collection remains a bottleneck. On the other hand, the integration of existing diffusion models, each specialized for different controls and operating in unique latent spaces, poses a challenge due to incompatible image resolutions and latent space embedding structures, hindering their joint use. Addressing these constraints, we present "PanGu-Draw", a novel latent diffusion model designed for resource-efficient text-to-image synthesis that adeptly accommodates multiple control signals. We first propose a resource-efficient Time-Decoupling Training Strategy, which splits the monolithic text-to-image model into structure and texture generators. Each generator is trained using a regimen that maximizes data utilization and computational efficiency, cutting data preparation by 48% and reducing training resources by 51%. Secondly, we introduce "Coop-Diffusion", an algorithm that enables the cooperative use of various pre-trained diffusion models with different latent spaces and predefined resolutions within a unified denoising process. This allows for multi-control image synthesis at arbitrary resolutions without the necessity for additional data or retraining. Empirical validations of Pangu-Draw show its exceptional prowess in text-to-image and multi-control image generation, suggesting a promising direction for future model training efficiencies and generation versatility. The largest 5B T2I PanGu-Draw model is released on the Ascend platform. Project page: $\href{https://pangu-draw.github.io}{this~https~URL}$
Abstract:Generating 3D faces from textual descriptions has a multitude of applications, such as gaming, movie, and robotics. Recent progresses have demonstrated the success of unconditional 3D face generation and text-to-3D shape generation. However, due to the limited text-3D face data pairs, text-driven 3D face generation remains an open problem. In this paper, we propose a text-guided 3D faces generation method, refer as TG-3DFace, for generating realistic 3D faces using text guidance. Specifically, we adopt an unconditional 3D face generation framework and equip it with text conditions, which learns the text-guided 3D face generation with only text-2D face data. On top of that, we propose two text-to-face cross-modal alignment techniques, including the global contrastive learning and the fine-grained alignment module, to facilitate high semantic consistency between generated 3D faces and input texts. Besides, we present directional classifier guidance during the inference process, which encourages creativity for out-of-domain generations. Compared to the existing methods, TG-3DFace creates more realistic and aesthetically pleasing 3D faces, boosting 9% multi-view consistency (MVIC) over Latent3D. The rendered face images generated by TG-3DFace achieve higher FID and CLIP score than text-to-2D face/image generation models, demonstrating our superiority in generating realistic and semantic-consistent textures.
Abstract:Cross-modal garment synthesis and manipulation will significantly benefit the way fashion designers generate garments and modify their designs via flexible linguistic interfaces.Current approaches follow the general text-to-image paradigm and mine cross-modal relations via simple cross-attention modules, neglecting the structural correspondence between visual and textual representations in the fashion design domain. In this work, we instead introduce DiffCloth, a diffusion-based pipeline for cross-modal garment synthesis and manipulation, which empowers diffusion models with flexible compositionality in the fashion domain by structurally aligning the cross-modal semantics. Specifically, we formulate the part-level cross-modal alignment as a bipartite matching problem between the linguistic Attribute-Phrases (AP) and the visual garment parts which are obtained via constituency parsing and semantic segmentation, respectively. To mitigate the issue of attribute confusion, we further propose a semantic-bundled cross-attention to preserve the spatial structure similarities between the attention maps of attribute adjectives and part nouns in each AP. Moreover, DiffCloth allows for manipulation of the generated results by simply replacing APs in the text prompts. The manipulation-irrelevant regions are recognized by blended masks obtained from the bundled attention maps of the APs and kept unchanged. Extensive experiments on the CM-Fashion benchmark demonstrate that DiffCloth both yields state-of-the-art garment synthesis results by leveraging the inherent structural information and supports flexible manipulation with region consistency.
Abstract:Recently, large-scale diffusion models, e.g., Stable diffusion and DallE2, have shown remarkable results on image synthesis. On the other hand, large-scale cross-modal pre-trained models (e.g., CLIP, ALIGN, and FILIP) are competent for various downstream tasks by learning to align vision and language embeddings. In this paper, we explore the possibility of jointly modeling generation and discrimination. Specifically, we propose DiffDis to unify the cross-modal generative and discriminative pretraining into one single framework under the diffusion process. DiffDis first formulates the image-text discriminative problem as a generative diffusion process of the text embedding from the text encoder conditioned on the image. Then, we propose a novel dual-stream network architecture, which fuses the noisy text embedding with the knowledge of latent images from different scales for image-text discriminative learning. Moreover, the generative and discriminative tasks can efficiently share the image-branch network structure in the multi-modality model. Benefiting from diffusion-based unified training, DiffDis achieves both better generation ability and cross-modal semantic alignment in one architecture. Experimental results show that DiffDis outperforms single-task models on both the image generation and the image-text discriminative tasks, e.g., 1.65% improvement on average accuracy of zero-shot classification over 12 datasets and 2.42 improvement on FID of zero-shot image synthesis.
Abstract:Recent advances in text-to-image diffusion models have achieved remarkable success in generating high-quality, realistic images from given text prompts. However, previous methods fail to perform accurate modality alignment between text concepts and generated images due to the lack of fine-level semantic guidance that successfully diagnoses the modality discrepancy. In this paper, we propose FineRewards to improve the alignment between text and images in text-to-image diffusion models by introducing two new fine-grained semantic rewards: the caption reward and the Semantic Segment Anything (SAM) reward. From the global semantic view, the caption reward generates a corresponding detailed caption that depicts all important contents in the synthetic image via a BLIP-2 model and then calculates the reward score by measuring the similarity between the generated caption and the given prompt. From the local semantic view, the SAM reward segments the generated images into local parts with category labels, and scores the segmented parts by measuring the likelihood of each category appearing in the prompted scene via a large language model, i.e., Vicuna-7B. Additionally, we adopt an assemble reward-ranked learning strategy to enable the integration of multiple reward functions to jointly guide the model training. Adapting results of text-to-image models on the MS-COCO benchmark show that the proposed semantic reward outperforms other baseline reward functions with a considerable margin on both visual quality and semantic similarity with the input prompt. Moreover, by adopting the assemble reward-ranked learning strategy, we further demonstrate that model performance is further improved when adapting under the unifying of the proposed semantic reward with the current image rewards.
Abstract:Existing text-guided image manipulation methods aim to modify the appearance of the image or to edit a few objects in a virtual or simple scenario, which is far from practical applications. In this work, we study a novel task on text-guided image manipulation on the entity level in the real world (eL-TGIM). The task imposes three basic requirements, (1) to edit the entity consistent with the text descriptions, (2) to preserve the entity-irrelevant regions, and (3) to merge the manipulated entity into the image naturally. To this end, we propose an elegant framework, dubbed as SeMani, forming the Semantic Manipulation of real-world images that can not only edit the appearance of entities but also generate new entities corresponding to the text guidance. To solve eL-TGIM, SeMani decomposes the task into two phases: the semantic alignment phase and the image manipulation phase. In the semantic alignment phase, SeMani incorporates a semantic alignment module to locate the entity-relevant region to be manipulated. In the image manipulation phase, SeMani adopts a generative model to synthesize new images conditioned on the entity-irrelevant regions and target text descriptions. We discuss and propose two popular generation processes that can be utilized in SeMani, the discrete auto-regressive generation with transformers and the continuous denoising generation with diffusion models, yielding SeMani-Trans and SeMani-Diff, respectively. We conduct extensive experiments on the real datasets CUB, Oxford, and COCO datasets to verify that SeMani can distinguish the entity-relevant and -irrelevant regions and achieve more precise and flexible manipulation in a zero-shot manner compared with baseline methods. Our codes and models will be released at https://github.com/Yikai-Wang/SeMani.
Abstract:Existing text-guided image manipulation methods aim to modify the appearance of the image or to edit a few objects in a virtual or simple scenario, which is far from practical application. In this work, we study a novel task on text-guided image manipulation on the entity level in the real world. The task imposes three basic requirements, (1) to edit the entity consistent with the text descriptions, (2) to preserve the text-irrelevant regions, and (3) to merge the manipulated entity into the image naturally. To this end, we propose a new transformer-based framework based on the two-stage image synthesis method, namely \textbf{ManiTrans}, which can not only edit the appearance of entities but also generate new entities corresponding to the text guidance. Our framework incorporates a semantic alignment module to locate the image regions to be manipulated, and a semantic loss to help align the relationship between the vision and language. We conduct extensive experiments on the real datasets, CUB, Oxford, and COCO datasets to verify that our method can distinguish the relevant and irrelevant regions and achieve more precise and flexible manipulation compared with baseline methods. The project homepage is \url{https://jawang19.github.io/manitrans}.
Abstract:Vision-Language Pre-training (VLP) models have shown remarkable performance on various downstream tasks. Their success heavily relies on the scale of pre-trained cross-modal datasets. However, the lack of large-scale datasets and benchmarks in Chinese hinders the development of Chinese VLP models and broader multilingual applications. In this work, we release a large-scale Chinese cross-modal dataset named Wukong, containing 100 million Chinese image-text pairs from the web. Wukong aims to benchmark different multi-modal pre-training methods to facilitate the VLP research and community development. Furthermore, we release a group of models pre-trained with various image encoders (ViT-B/ViT-L/SwinT) and also apply advanced pre-training techniques into VLP such as locked-image text tuning, token-wise similarity in contrastive learning, and reduced-token interaction. Extensive experiments and a deep benchmarking of different downstream tasks are also provided. Experiments show that Wukong can serve as a promising Chinese pre-training dataset and benchmark for different cross-modal learning methods. For the zero-shot image classification task on 10 datasets, our model achieves an average accuracy of 73.03%. For the image-text retrieval task,our model achieves a mean recall of 71.6% on AIC-ICC which is 12.9% higher than the result of WenLan 2.0. More information can refer to https://wukong-dataset.github.io/wukong-dataset/.