Zhongjie Duan

Chengyu Wang, Zhongjie Duan, Bingyan Liu et al.

Text-to-image synthesis for the Chinese language poses unique challenges due to its large vocabulary size, and intricate character relationships. While existing diffusion models have shown promise in generating images from textual descriptions, they often neglect domain-specific contexts and lack robustness in handling the Chinese language. This paper introduces PAI-Diffusion, a comprehensive framework that addresses these limitations. PAI-Diffusion incorporates both general and domain-specific Chinese diffusion models, enabling the generation of contextually relevant images. It explores the potential of using LoRA and ControlNet for fine-grained image style transfer and image editing, empowering users with enhanced control over image generation. Moreover, PAI-Diffusion seamlessly integrates with Alibaba Cloud's Machine Learning Platform for AI, providing accessible and scalable solutions. All the Chinese diffusion model checkpoints, LoRAs, and ControlNets, including domain-specific ones, are publicly available. A user-friendly Chinese WebUI and the diffusers-api elastic inference toolkit, also open-sourced, further facilitate the easy deployment of PAI-Diffusion models in various environments, making it a valuable resource for Chinese text-to-image synthesis.

Zhiwen Li, Zhongjie Duan, Jinyan Ye et al.

Replicating In-Context Learning (ICL) in computer vision remains challenging due to task heterogeneity. We propose \textbf{VIRAL}, a framework that elicits visual reasoning from a pre-trained image editing model by formulating ICL as conditional generation via visual analogy ($x_s : x_t :: x_q : y_q$). We adapt a frozen Diffusion Transformer (DiT) using role-aware multi-image conditioning and introduce a Mixture-of-Experts LoRA to mitigate gradient interference across diverse tasks. Additionally, to bridge the gaps in current visual context datasets, we curate a large-scale dataset spanning perception, restoration, and editing. Experiments demonstrate that VIRAL outperforms existing methods, validating that a unified V-ICL paradigm can handle the majority of visual tasks, including open-domain editing. Our code is available at https://anonymous.4open.science/r/VIRAL-744A

Zhongjie Duan, Lizhou You, Chengyu Wang et al.

In recent years, diffusion models have emerged as the most powerful approach in image synthesis. However, applying these models directly to video synthesis presents challenges, as it often leads to noticeable flickering contents. Although recently proposed zero-shot methods can alleviate flicker to some extent, we still struggle to generate coherent videos. In this paper, we propose DiffSynth, a novel approach that aims to convert image synthesis pipelines to video synthesis pipelines. DiffSynth consists of two key components: a latent in-iteration deflickering framework and a video deflickering algorithm. The latent in-iteration deflickering framework applies video deflickering to the latent space of diffusion models, effectively preventing flicker accumulation in intermediate steps. Additionally, we propose a video deflickering algorithm, named patch blending algorithm, that remaps objects in different frames and blends them together to enhance video consistency. One of the notable advantages of DiffSynth is its general applicability to various video synthesis tasks, including text-guided video stylization, fashion video synthesis, image-guided video stylization, video restoring, and 3D rendering. In the task of text-guided video stylization, we make it possible to synthesize high-quality videos without cherry-picking. The experimental results demonstrate the effectiveness of DiffSynth. All videos can be viewed on our project page. Source codes will also be released.

Zhongjie Duan, Chengyu Wang, Cen Chen et al.

With the emergence of diffusion models and rapid development in image processing, it has become effortless to generate fancy images in tasks such as style transfer and image editing. However, these impressive image processing approaches face consistency issues in video processing. In this paper, we propose a powerful model-free toolkit called FastBlend to address the consistency problem for video processing. Based on a patch matching algorithm, we design two inference modes, including blending and interpolation. In the blending mode, FastBlend eliminates video flicker by blending the frames within a sliding window. Moreover, we optimize both computational efficiency and video quality according to different application scenarios. In the interpolation mode, given one or more keyframes rendered by diffusion models, FastBlend can render the whole video. Since FastBlend does not modify the generation process of diffusion models, it exhibits excellent compatibility. Extensive experiments have demonstrated the effectiveness of FastBlend. In the blending mode, FastBlend outperforms existing methods for video deflickering and video synthesis. In the interpolation mode, FastBlend surpasses video interpolation and model-based video processing approaches. The source codes have been released on GitHub.

Ruyao Xu, Taolin Zhang, Chengyu Wang et al.

Knowledge-Enhanced Pre-trained Language Models (KEPLMs) improve the performance of various downstream NLP tasks by injecting knowledge facts from large-scale Knowledge Graphs (KGs). However, existing methods for pre-training KEPLMs with relational triples are difficult to be adapted to close domains due to the lack of sufficient domain graph semantics. In this paper, we propose a Knowledge-enhanced lANGuAge Representation learning framework for various clOsed dOmains (KANGAROO) via capturing the implicit graph structure among the entities. Specifically, since the entity coverage rates of closed-domain KGs can be relatively low and may exhibit the global sparsity phenomenon for knowledge injection, we consider not only the shallow relational representations of triples but also the hyperbolic embeddings of deep hierarchical entity-class structures for effective knowledge fusion.Moreover, as two closed-domain entities under the same entity-class often have locally dense neighbor subgraphs counted by max point biconnected component, we further propose a data augmentation strategy based on contrastive learning over subgraphs to construct hard negative samples of higher quality. It makes the underlying KELPMs better distinguish the semantics of these neighboring entities to further complement the global semantic sparsity. In the experiments, we evaluate KANGAROO over various knowledge-aware and general NLP tasks in both full and few-shot learning settings, outperforming various KEPLM training paradigms performance in closed-domains significantly.

Zhongjie Duan, Hong Zhang, Yingda Chen

Controllable diffusion methods have substantially expanded the practical utility of diffusion models, but they are typically developed as isolated, backbone-specific systems with incompatible training pipelines, parameter formats, and runtime hooks. This fragmentation makes it difficult to reuse infrastructure across tasks, transfer capabilities across backbones, or compose multiple controls within a single generation pipeline. We present Diffusion Templates, a unified and open plugin framework that decouples base-model inference from controllable capability injection. The framework is organized around three components: Template models that map arbitrary task-specific inputs to an intermediate capability representation, a Template cache that functions as a standardized interface for capability injection, and a Template pipeline that loads, merges, and injects one or more Template caches into the base diffusion runtime. Because the interface is defined at the systems level rather than tied to a specific control architecture, heterogeneous capability carriers such as KV-Cache and LoRA can be supported under the same abstraction. Based on this design, we build a diverse model zoo spanning structural control, brightness adjustment, color adjustment, image editing, super-resolution, sharpness enhancement, aesthetic alignment, content reference, local inpainting, and age control. These case studies show that Diffusion Templates can unify a broad range of controllable generation tasks while preserving modularity, composability, and practical extensibility across rapidly evolving diffusion backbones. All resources will be open sourced, including code, models, and datasets.

Jinyan Ye, Zhongjie Duan, Zhiwen Li et al.

Inference-time scaling offers a versatile paradigm for aligning visual generative models with downstream objectives without parameter updates. However, existing approaches that optimize the high-dimensional initial noise suffer from severe inefficiency, as many search directions exert negligible influence on the final generation. We show that this inefficiency is closely related to a spectral bias in generative dynamics: model sensitivity to initial perturbations diminishes rapidly as frequency increases. Building on this insight, we propose Spectral Evolution Search (SES), a plug-and-play framework for initial noise optimization that executes gradient-free evolutionary search within a low-frequency subspace. Theoretically, we derive the Spectral Scaling Prediction from perturbation propagation dynamics, which explains the systematic differences in the impact of perturbations across frequencies. Extensive experiments demonstrate that SES significantly advances the Pareto frontier of generation quality versus computational cost, consistently outperforming strong baselines under equivalent budgets.

Hong Zhang, Zhongjie Duan, Xingjun Wang et al.

Recent advancements in diffusion models have significantly advanced text-to-image generation, yet global text prompts alone remain insufficient for achieving fine-grained control over individual entities within an image. To address this limitation, we present EliGen, a novel framework for Entity-level controlled image Generation. Firstly, we put forward regional attention, a mechanism for diffusion transformers that requires no additional parameters, seamlessly integrating entity prompts and arbitrary-shaped spatial masks. By contributing a high-quality dataset with fine-grained spatial and semantic entity-level annotations, we train EliGen to achieve robust and accurate entity-level manipulation, surpassing existing methods in both spatial precision and image quality. Additionally, we propose an inpainting fusion pipeline, extending its capabilities to multi-entity image inpainting tasks. We further demonstrate its flexibility by integrating it with other open-source models such as IP-Adapter, In-Context LoRA and MLLM, unlocking new creative possibilities. The source code, model, and dataset are published at https://github.com/modelscope/DiffSynth-Studio.git.

Zhongjie Duan, Chengyu Wang, Cen Chen et al.

Toon shading is a type of non-photorealistic rendering task of animation. Its primary purpose is to render objects with a flat and stylized appearance. As diffusion models have ascended to the forefront of image synthesis methodologies, this paper delves into an innovative form of toon shading based on diffusion models, aiming to directly render photorealistic videos into anime styles. In video stylization, extant methods encounter persistent challenges, notably in maintaining consistency and achieving high visual quality. In this paper, we model the toon shading problem as four subproblems: stylization, consistency enhancement, structure guidance, and colorization. To address the challenges in video stylization, we propose an effective toon shading approach called \textit{Diffutoon}. Diffutoon is capable of rendering remarkably detailed, high-resolution, and extended-duration videos in anime style. It can also edit the content according to prompts via an additional branch. The efficacy of Diffutoon is evaluated through quantitive metrics and human evaluation. Notably, Diffutoon surpasses both open-source and closed-source baseline approaches in our experiments. Our work is accompanied by the release of both the source code and example videos on Github (Project page: https://ecnu-cilab.github.io/DiffutoonProjectPage/).

Hong Zhang, Zhongjie Duan, Xingjun Wang et al.

Unified multimodal generative models aim to integrate image understanding and generation abilities, offering significant advantages in harnessing multimodal corpora, particularly interleaved text-image data. However, existing unified models exhibit limitations in image synthesis quality, autoregressive error accumulation, and image editing capability. In this work, we propose Nexus-Gen, a novel architecture that unifies image understanding, generation, and editing tasks in a shared image embedding space. This shared space serves as a bridge for the autoregressive and diffusion models, which seamlessly integrates their complementary strengths in cross-modal modeling. To mitigate the severe error accumulation during autoregressive embedding prediction, we propose a novel prefilled autoregression strategy that aligns training-inference dynamics by prefilling input sequences with learnable embeddings. After multi-stage and multi-task training on our constructed large-scale dataset with 26.3 million samples, Nexus-Gen achieves state-of-the-art performance on the evaluation benchmarks spanning image understanding, generation and editing tasks. All models, datasets, and source codes are released in https://github.com/modelscope/Nexus-Gen to facilitate further advancements across the field.

Die Chen, Zhongjie Duan, Zhiwen Li et al.

Recent breakthroughs in text-to-image diffusion models have significantly enhanced both the visual fidelity and semantic controllability of generated images. However, fine-grained control over aesthetic attributes remains challenging, especially when users require continuous and intensity-specific adjustments. Existing approaches often rely on vague textual prompts, which are inherently ambiguous in expressing both the aesthetic semantics and the desired intensity, or depend on costly human preference data for alignment, limiting their scalability and practicality. To address these limitations, we propose AttriCtrl, a plug-and-play framework for precise and continuous control of aesthetic attributes. Specifically, we quantify abstract aesthetics by leveraging semantic similarity from pre-trained vision-language models, and employ a lightweight value encoder that maps scalar intensities in $[0,1]$ to learnable embeddings within diffusion-based generation. This design enables intuitive and customizable aesthetic manipulation, with minimal training overhead and seamless integration into existing generation pipelines. Extensive experiments demonstrate that AttriCtrl achieves accurate control over individual attributes as well as flexible multi-attribute composition. Moreover, it is fully compatible with popular open-source controllable generation frameworks, showcasing strong integration capability and practical utility across diverse generation scenarios.

Zhiwen Li, Zhongjie Duan, Die Chen et al.

Despite recent advances in photorealistic image generation through large-scale models like FLUX and Stable Diffusion v3, the practical deployment of these architectures remains constrained by their inherent intractability to parameter fine-tuning. While low-rank adaptation (LoRA) have demonstrated efficacy in enabling model customization with minimal parameter overhead, the effective utilization of distributed open-source LoRA modules faces three critical challenges: sparse metadata annotation, the requirement for zero-shot adaptation capabilities, and suboptimal fusion strategies for multi-LoRA fusion strategies. To address these limitations, we introduce a novel framework that enables semantic-driven LoRA retrieval and dynamic aggregation through two key components: (1) weight encoding-base LoRA retriever that establishes a shared semantic space between LoRA parameter matrices and text prompts, eliminating dependence on original training data, and (2) fine-grained gated fusion mechanism that computes context-specific fusion weights across network layers and diffusion timesteps to optimally integrate multiple LoRA modules during generation. Our approach achieves significant improvement in image generation perfermance, thereby facilitating scalable and data-efficient enhancement of foundational models. This work establishes a critical bridge between the fragmented landscape of community-developed LoRAs and practical deployment requirements, enabling collaborative model evolution through standardized adapter integration.

Zhongjie Duan, Chengyu Wang, Cen Chen et al.

In recent years, diffusion models have become the most popular and powerful methods in the field of image synthesis, even rivaling human artists in artistic creativity. However, the key issue currently limiting the application of diffusion models is its extremely slow generation process. Although several methods were proposed to speed up the generation process, there still exists a trade-off between efficiency and quality. In this paper, we first provide a detailed theoretical and empirical analysis of the generation process of the diffusion models based on schedulers. We transform the designing problem of schedulers into the determination of several parameters, and further transform the accelerated generation process into an expansion process of the linear subspace. Based on these analyses, we consequently propose a novel method called Optimal Linear Subspace Search (OLSS), which accelerates the generation process by searching for the optimal approximation process of the complete generation process in the linear subspaces spanned by latent variables. OLSS is able to generate high-quality images with a very small number of steps. To demonstrate the effectiveness of our method, we conduct extensive comparative experiments on open-source diffusion models. Experimental results show that with a given number of steps, OLSS can significantly improve the quality of generated images. Using an NVIDIA A100 GPU, we make it possible to generate a high-quality image by Stable Diffusion within only one second without other optimization techniques.

Zhongjie Duan, Qianyi Zhao, Cen Chen et al.

The emergence of diffusion models has significantly advanced image synthesis. The recent studies of model interaction and self-corrective reasoning approach in large language models offer new insights for enhancing text-to-image models. Inspired by these studies, we propose a novel method called ArtAug for enhancing text-to-image models in this paper. To the best of our knowledge, ArtAug is the first one that improves image synthesis models via model interactions with understanding models. In the interactions, we leverage human preferences implicitly learned by image understanding models to provide fine-grained suggestions for image synthesis models. The interactions can modify the image content to make it aesthetically pleasing, such as adjusting exposure, changing shooting angles, and adding atmospheric effects. The enhancements brought by the interaction are iteratively fused into the synthesis model itself through an additional enhancement module. This enables the synthesis model to directly produce aesthetically pleasing images without any extra computational cost. In the experiments, we train the ArtAug enhancement module on existing text-to-image models. Various evaluation metrics consistently demonstrate that ArtAug enhances the generative capabilities of text-to-image models without incurring additional computational costs. The source code and models will be released publicly.

Zhongjie Duan, Wenmeng Zhou, Cen Chen et al.

Recently, advancements in video synthesis have attracted significant attention. Video synthesis models such as AnimateDiff and Stable Video Diffusion have demonstrated the practical applicability of diffusion models in creating dynamic visual content. The emergence of SORA has further spotlighted the potential of video generation technologies. Nonetheless, the extension of video lengths has been constrained by the limitations in computational resources. Most existing video synthesis models can only generate short video clips. In this paper, we propose a novel post-tuning methodology for video synthesis models, called ExVideo. This approach is designed to enhance the capability of current video synthesis models, allowing them to produce content over extended temporal durations while incurring lower training expenditures. In particular, we design extension strategies across common temporal model architectures respectively, including 3D convolution, temporal attention, and positional embedding. To evaluate the efficacy of our proposed post-tuning approach, we conduct extension training on the Stable Video Diffusion model. Our approach augments the model's capacity to generate up to $5\times$ its original number of frames, requiring only 1.5k GPU hours of training on a dataset comprising 40k videos. Importantly, the substantial increase in video length doesn't compromise the model's innate generalization capabilities, and the model showcases its advantages in generating videos of diverse styles and resolutions. We will release the source code and the enhanced model publicly.