Diffusion-Based Image Generation

Unified conditional image generation remains difficult because different tasks depend on fundamentally different internal representations. Some require conceptual understanding for semantic synthesis, while others rely on localization cues for spatial precision. Forcing these heterogeneous tasks to share a single representation leads to concept-localization representational conflict. To address this issue, we propose CoLoGen, a unified diffusion framework that progressively learns and reconciles this concept-localization duality. CoLoGen uses a staged curriculum that first builds core conceptual and localization abilities, then adapts them to diverse visual conditions, and finally refines their synergy for complex instruction-driven tasks. Central to this process is the Progressive Representation Weaving (PRW) module, which dynamically routes features to specialized experts and stably integrates their outputs across stages. Experiments on editing, controllable generation, and customized generation show that CoLoGen achieves competitive or superior performance, offering a principled representational perspective for unified image generation.

Digitizing humans and synthesizing photorealistic avatars with explicit 3D pose and camera controls are central to VR, telepresence, and entertainment. Existing skinning-based workflows require laborious manual rigging or template-based fittings, while neural volumetric methods rely on canonical templates and re-optimization for each unseen pose. We present PoseCraft, a diffusion framework built around tokenized 3D interface: instead of relying only on rasterized geometry as 2D control images, we encode sparse 3D landmarks and camera extrinsics as discrete conditioning tokens and inject them into diffusion via cross-attention. Our approach preserves 3D semantics by avoiding 2D re-projection ambiguity under large pose and viewpoint changes, and produces photorealistic imagery that faithfully captures identity and appearance. To train and evaluate at scale, we also implement GenHumanRF, a data generation workflow that renders diverse supervision from volumetric reconstructions. Our experiments show that PoseCraft achieves significant perceptual quality improvement over diffusion-centric methods, and attains better or comparable metrics to latest volumetric rendering SOTA while better preserving fabric and hair details.

Visual counterfactual explanations aim to reveal the minimal semantic modifications that can alter a model's prediction, providing causal and interpretable insights into deep neural networks. However, existing diffusion-based counterfactual generation methods are often computationally expensive, slow to sample, and imprecise in localizing the modified regions. To address these limitations, we propose MaskDiME, a simple, fast, yet effective diffusion framework that unifies semantic consistency and spatial precision through localized sampling. Our approach adaptively focuses on decision-relevant regions to achieve localized and semantically consistent counterfactual generation while preserving high image fidelity. Our training-free framework, MaskDiME, performs inference over 30x faster than the baseline and achieves comparable or state-of-the-art performance across five benchmark datasets spanning diverse visual domains, establishing a practical and generalizable solution for efficient counterfactual explanation.

Sketches offer designers a concise yet expressive medium for early-stage fashion ideation by specifying structure, silhouette, and spatial relationships, while textual descriptions complement sketches to convey material, color, and stylistic details. Effectively combining textual and visual modalities requires adherence to the sketch visual structure when leveraging the guidance of localized attributes from text. We present LOcalized Text and Sketch with multi-level guidance (LOTS), a framework that enhances fashion image generation by combining global sketch guidance with multiple localized sketch-text pairs. LOTS employs a Multi-level Conditioning Stage to independently encode local features within a shared latent space while maintaining global structural coordination. Then, the Diffusion Pair Guidance stage integrates both local and global conditioning via attention-based guidance within the diffusion model's multi-step denoising process. To validate our method, we develop Sketchy, the first fashion dataset where multiple text-sketch pairs are provided per image. Sketchy provides high-quality, clean sketches with a professional look and consistent structure. To assess robustness beyond this setting, we also include an "in the wild" split with non-expert sketches, featuring higher variability and imperfections. Experiments demonstrate that our method strengthens global structural adherence while leveraging richer localized semantic guidance, achieving improvement over state-of-the-art. The dataset, platform, and code are publicly available.

Multi-Instance Generation has advanced significantly in spatial placement and attribute binding. However, existing approaches still face challenges in fine-grained semantic understanding, particularly when dealing with complex textual descriptions. To overcome these limitations, we propose DEIG, a novel framework for fine-grained and controllable multi-instance generation. DEIG integrates an Instance Detail Extractor (IDE) that transforms text encoder embeddings into compact, instance-aware representations, and a Detail Fusion Module (DFM) that applies instance-based masked attention to prevent attribute leakage across instances. These components enable DEIG to generate visually coherent multi-instance scenes that precisely match rich, localized textual descriptions. To support fine-grained supervision, we construct a high-quality dataset with detailed, compositional instance captions generated by VLMs. We also introduce DEIG-Bench, a new benchmark with region-level annotations and multi-attribute prompts for both humans and objects. Experiments demonstrate that DEIG consistently outperforms existing approaches across multiple benchmarks in spatial consistency, semantic accuracy, and compositional generalization. Moreover, DEIG functions as a plug-and-play module, making it easily integrable into standard diffusion-based pipelines.

Diffusion Transformers (DiT) have emerged as a widely adopted backbone for high-fidelity image and video generation, yet their iterative denoising process incurs high computational costs. Existing training-free acceleration methods rely on feature caching and reuse under the assumption of temporal stability. However, reusing features for multiple steps may lead to latent drift and visual degradation. We observe that model outputs evolve smoothly along much of the diffusion trajectory, enabling principled predictions rather than naive reuse. Based on this insight, we propose PrediT, a training-free acceleration framework that formulates feature prediction as a linear multistep problem. We employ classical linear multistep methods to forecast future model outputs from historical information, combined with a corrector that activates in high-dynamics regions to prevent error accumulation. A dynamic step modulation mechanism adaptively adjusts the prediction horizon by monitoring the feature change rate. Together, these components enable substantial acceleration while preserving generation fidelity. Extensive experiments validate that our method achieves up to $5.54\times$ latency reduction across various DiT-based image and video generation models, while incurring negligible quality degradation.

We present Unified Latents (UL), a framework for learning latent representations that are jointly regularized by a diffusion prior and decoded by a diffusion model. By linking the encoder's output noise to the prior's minimum noise level, we obtain a simple training objective that provides a tight upper bound on the latent bitrate. On ImageNet-512, our approach achieves competitive FID of 1.4, with high reconstruction quality (PSNR) while requiring fewer training FLOPs than models trained on Stable Diffusion latents. On Kinetics-600, we set a new state-of-the-art FVD of 1.3.

Diffusion Transformers (DiTs) have achieved state-of-the-art performance in image and video generation, but their success comes at the cost of heavy computation. This inefficiency is largely due to the fixed tokenization process, which uses constant-sized patches throughout the entire denoising phase, regardless of the content's complexity. We propose dynamic tokenization, an efficient test-time strategy that varies patch sizes based on content complexity and the denoising timestep. Our key insight is that early timesteps only require coarser patches to model global structure, while later iterations demand finer (smaller-sized) patches to refine local details. During inference, our method dynamically reallocates patch sizes across denoising steps for image and video generation and substantially reduces cost while preserving perceptual generation quality. Extensive experiments demonstrate the effectiveness of our approach: it achieves up to $3.52\times$ and $3.2\times$ speedup on FLUX-1.Dev and Wan $2.1$, respectively, without compromising the generation quality and prompt adherence.

Inspired by non-equilibrium thermodynamics, diffusion models have achieved state-of-the-art performance in generative modeling. However, their iterative sampling nature results in high inference latency. While recent distillation techniques accelerate sampling, they discard intermediate trajectory steps. This sparse supervision leads to a loss of structural information and introduces significant discretization errors. To mitigate this, we propose B-DENSE, a novel framework that leverages multi-branch trajectory alignment. We modify the student architecture to output $K$-fold expanded channels, where each subset corresponds to a specific branch representing a discrete intermediate step in the teacher's trajectory. By training these branches to simultaneously map to the entire sequence of the teacher's target timesteps, we enforce dense intermediate trajectory alignment. Consequently, the student model learns to navigate the solution space from the earliest stages of training, demonstrating superior image generation quality compared to baseline distillation frameworks.

Recent studies have explored the combination of multiple LoRAs to simultaneously generate user-specified subjects and styles. However, most existing approaches fuse LoRA weights using static statistical heuristics that deviate from LoRA's original purpose of learning adaptive feature adjustments and ignore the randomness of sampled inputs. To address this, we propose a dynamic training-free fusion framework that operates throughout the generation process. During the forward pass, at each LoRA-applied layer, we dynamically compute the KL divergence between the base model's original features and those produced by subject and style LoRAs, respectively, and adaptively select the most appropriate weights for fusion. In the reverse denoising stage, we further refine the generation trajectory by dynamically applying gradient-based corrections derived from objective metrics such as CLIP and DINO scores, providing continuous semantic and stylistic guidance. By integrating these two complementary mechanisms-feature-level selection and metric-guided latent adjustment-across the entire diffusion timeline, our method dynamically achieves coherent subject-style synthesis without any retraining. Extensive experiments across diverse subject-style combinations demonstrate that our approach consistently outperforms state-of-the-art LoRA fusion methods both qualitatively and quantitatively.

The slow iterative sampling nature remains a major bottleneck for the practical deployment of diffusion and flow-based generative models. While consistency models (CMs) represent a state-of-the-art distillation-based approach for efficient generation, their large-scale application is still limited by two key issues: training instability and inflexible sampling. Existing methods seek to mitigate these problems through architectural adjustments or regularized objectives, yet overlook the critical reliance on trajectory selection. In this work, we first conduct an analysis on these two limitations: training instability originates from loss divergence induced by unstable self-supervised term, whereas sampling inflexibility arises from error accumulation. Based on these insights and analysis, we propose the Dual-End Consistency Model (DE-CM) that selects vital sub-trajectory clusters to achieve stable and effective training. DE-CM decomposes the PF-ODE trajectory and selects three critical sub-trajectories as optimization targets. Specifically, our approach leverages continuous-time CMs objectives to achieve few-step distillation and utilizes flow matching as a boundary regularizer to stabilize the training process. Furthermore, we propose a novel noise-to-noisy (N2N) mapping that can map noise to any point, thereby alleviating the error accumulation in the first step. Extensive experimental results show the effectiveness of our method: it achieves a state-of-the-art FID score of 1.70 in one-step generation on the ImageNet 256x256 dataset, outperforming existing CM-based one-step approaches.

Leveraging representation encoders for generative modeling offers a path for efficient, high-fidelity synthesis. However, standard diffusion transformers fail to converge on these representations directly. While recent work attributes this to a capacity bottleneck proposing computationally expensive width scaling of diffusion transformers we demonstrate that the failure is fundamentally geometric. We identify Geometric Interference as the root cause: standard Euclidean flow matching forces probability paths through the low-density interior of the hyperspherical feature space of representation encoders, rather than following the manifold surface. To resolve this, we propose Riemannian Flow Matching with Jacobi Regularization (RJF). By constraining the generative process to the manifold geodesics and correcting for curvature-induced error propagation, RJF enables standard Diffusion Transformer architectures to converge without width scaling. Our method RJF enables the standard DiT-B architecture (131M parameters) to converge effectively, achieving an FID of 3.37 where prior methods fail to converge. Code: https://github.com/amandpkr/RJF

Diffusion Transformers are fundamental for video and image generation, but their efficiency is bottlenecked by the quadratic complexity of attention. While block sparse attention accelerates computation by attending only critical key-value blocks, it suffers from degradation at high sparsity by discarding context. In this work, we discover that attention scores of non-critical blocks exhibit distributional stability, allowing them to be approximated accurately and efficiently rather than discarded, which is essentially important for sparse attention design. Motivated by this key insight, we propose PISA, a training-free Piecewise Sparse Attention that covers the full attention span with sub-quadratic complexity. Unlike the conventional keep-or-drop paradigm that directly drop the non-critical block information, PISA introduces a novel exact-or-approximate strategy: it maintains exact computation for critical blocks while efficiently approximating the remainder through block-wise Taylor expansion. This design allows PISA to serve as a faithful proxy to full attention, effectively bridging the gap between speed and quality. Experimental results demonstrate that PISA achieves 1.91 times and 2.57 times speedups on Wan2.1-14B and Hunyuan-Video, respectively, while consistently maintaining the highest quality among sparse attention methods. Notably, even for image generation on FLUX, PISA achieves a 1.2 times acceleration without compromising visual quality. Code is available at: https://github.com/xie-lab-ml/piecewise-sparse-attention.

We propose Ambient Dataloops, an iterative framework for refining datasets that makes it easier for diffusion models to learn the underlying data distribution. Modern datasets contain samples of highly varying quality, and training directly on such heterogeneous data often yields suboptimal models. We propose a dataset-model co-evolution process; at each iteration of our method, the dataset becomes progressively higher quality, and the model improves accordingly. To avoid destructive self-consuming loops, at each generation, we treat the synthetically improved samples as noisy, but at a slightly lower noisy level than the previous iteration, and we use Ambient Diffusion techniques for learning under corruption. Empirically, Ambient Dataloops achieve state-of-the-art performance in unconditional and text-conditional image generation and de novo protein design. We further provide a theoretical justification for the proposed framework that captures the benefits of the data looping procedure.

Substation meters play a critical role in monitoring and ensuring the stable operation of power grids, yet their detection of cracks and other physical defects is often hampered by a severe scarcity of annotated samples. To address this few-shot generation challenge, we propose a novel framework that integrates Knowledge Embedding and Hypernetwork-Guided Conditional Control into a Stable Diffusion pipeline, enabling realistic and controllable synthesis of defect images from limited data. First, we bridge the substantial domain gap between natural-image pre-trained models and industrial equipment by fine-tuning a Stable Diffusion backbone using DreamBooth-style knowledge embedding. This process encodes the unique structural and textural priors of substation meters, ensuring generated images retain authentic meter characteristics. Second, we introduce a geometric crack modeling module that parameterizes defect attributes--such as location, length, curvature, and branching pattern--to produce spatially constrained control maps. These maps provide precise, pixel-level guidance during generation. Third, we design a lightweight hypernetwork that dynamically modulates the denoising process of the diffusion model in response to the control maps and high-level defect descriptors, achieving a flexible balance between generation fidelity and controllability. Extensive experiments on a real-world substation meter dataset demonstrate that our method substantially outperforms existing augmentation and generation baselines. It reduces Frechet Inception Distance (FID) by 32.7%, increases diversity metrics, and--most importantly--boosts the mAP of a downstream defect detector by 15.3% when trained on augmented data. The framework offers a practical, high-quality data synthesis solution for industrial inspection systems where defect samples are rare.

Expert-annotated training data remains the critical bottleneck for AI in histopathology, particularly for rare pathologies where even dozens of cases may be unavailable. While data augmentation offers a solution, existing methods fail to generate sufficiently realistic lesion morphologies that preserve tissue-specific architectures. Here we present PathoGen, a diffusion-based generative model enabling controllable, high-fidelity lesion inpainting into benign histopathology images. We validate PathoGen across four datasets representing kidney, skin, breast, and prostate pathology. Quantitative assessment confirms PathoGen outperforms state-of-the-art baselines in image fidelity and distributional similarity. Evaluation by six expert pathologists revealed that synthetic images by PathoGen were only marginally distinguished from real tissue image slightly above chance (57.75% accuracy), demonstrating strong perceptual realism of PathoGen-generated lesions. PathoGen achieved the highest win rate (35.4%) when pathologists ranked generation quality against all baselines. Crucially, augmenting training sets with PathoGen-synthesized lesions improves segmentation Dice scores by up to 0.18 compared to traditional augmentations, with maximum benefit in data-scarce regimes. By simultaneously generating realistic morphology and pixel-level annotations, PathoGen effectively addresses both data scarcity and annotation cost, two critical bottlenecks in computational pathology development.

This paper studies the training-testing discrepancy (a.k.a. exposure bias) problem for improving the diffusion models. During training, the input of a prediction network at one training timestep is the corresponding ground-truth noisy data that is an interpolation of the noise and the data, and during testing, the input is the generated noisy data. We present a novel training approach, named MixFlow, for improving the performance. Our approach is motivated by the Slow Flow phenomenon: the ground-truth interpolation that is the nearest to the generated noisy data at a given sampling timestep is observed to correspond to a higher-noise timestep (termed slowed timestep), i.e., the corresponding ground-truth timestep is slower than the sampling timestep. MixFlow leverages the interpolations at the slowed timesteps, named slowed interpolation mixture, for post-training the prediction network for each training timestep. Experiments over class-conditional image generation (including SiT, REPA, and RAE) and text-to-image generation validate the effectiveness of our approach. Our approach MixFlow over the RAE models achieve strong generation results on ImageNet: 1.43 FID (without guidance) and 1.10 (with guidance) at 256 x 256, and 1.55 FID (without guidance) and 1.10 (with guidance) at 512 x 512.

In diffusion and flow-matching generative models, guidance techniques are widely used to improve sample quality and consistency. Classifier-free guidance (CFG) is the de facto choice in modern systems and achieves this by contrasting conditional and unconditional samples. Recent work explores contrasting negative samples at inference using a weaker model, via strong/weak model pairs, attention-based masking, stochastic block dropping, or perturbations to the self-attention energy landscape. While these strategies refine the generation quality, they still lack a reliable control over the granularity or difficulty of the negative samples, and target-layer selection is often fixed. We propose Exponential Moving Average Guidance (EMAG), a training-free mechanism that modifies attention at inference time in diffusion transformers, with a statistics-based, adaptive layer-selection rule. Unlike prior methods, EMAG produces harder, semantically faithful negatives (fine-grained degradations), surfacing difficult failure modes, enabling the denoiser to refine subtle artifacts, boosting the quality and human preference score (HPS) by +0.54 over CFG. We further demonstrate that EMAG naturally composes with advanced orthogonal guidance techniques, such as APG and CADS, further improving HPS.

Generating realistic cast shadows for inserted foreground objects requires reasoning about scene geometry and illumination. However, most learning-based approaches treat shadow generation as an image translation problem and capture these physical relationships only implicitly. This often results in misaligned or implausible shadows. Motivated by the physics of shadow formation, we introduce explicit geometric guidance for outdoor shadow generation. Given a composite image and a foreground object mask, we recover approximate scene geometry and estimate a dominant light direction to derive a coarse shadow estimate via geometric reasoning. While coarse, this estimate provides a spatial anchor for shadow placement. Because illumination cannot always be uniquely inferred from a single image, we predict confidence scores for both lighting and shadow cues and use them to regulate their influence during generation. These cues (shadow mask, light direction, and their confidence scores) condition a diffusion-based generator that refines the estimate into a realistic shadow. Experiments on DESOBAV2 show substantially improved shadow-region fidelity and localization, with an overall 23% lower shadow-region RMSE and 30% lower shadow-mask BER than the prior state-of-the-art method.

3D head stylization enables expressive reimagining of human faces for creative visual experiences in digital media. Existing 3D-aware methods often require computationally intensive optimization or per-style fine-tuning, limiting flexibility and user control. To overcome these challenges, we introduce StyleFusion360, a diffusion-based framework for multi-view consistent, identity-preserving 3D head stylization from a single style reference image, without per-style training. Our approach enhances the Style Fusion Attention mechanism with a style-conditioned key modulation mechanism that aligns content and style representations for fine-grained and controllable stylization. We further provide a user-controllable slider for adjusting stylization intensity. In addition, StyleFusion360 supports local multi-edit stylization, enabling targeted edits such as modifying hair or eyes independently. Extensive experiments on FFHQ and RenderMe360 demonstrate that StyleFusion360 produces high-quality, controllable, and visually compelling stylizations, outperforming state-of-the-art GAN- and diffusion-based methods across diverse style domains.

Anomaly generation is often framed as few-shot fine-tuning with anomalous samples, which contradicts the scarcity that motivates generation and tends to overfit category priors. We tackle the setting where no real anomaly samples or training are available. We propose Delta-Denoising (DeltaDeno), a training-free zero-shot anomaly generation method that localizes and edits defects by contrasting two diffusion branches driven by a minimal prompt pair under a shared schedule. By accumulating per-step denoising deltas into an image-specific localization map, we obtain a mask to guide the latent inpainting during later diffusion steps and preserve the surrounding context while generating realistic local defects. To improve stability and control, DeltaDeno performs token-level prompt refinement that aligns shared content and strengthens anomaly tokens, and applies a spatial attention bias restricted to anomaly tokens in the predicted region. Experiments on public datasets show that DeltaDeno achieves great generation, realism and consistent gains in downstream detection performance. Code will be made publicly available at https://github.com/CROVO1026/DeltaDeno.

Diffusion models achieve state-of-the-art generative performance but remain computationally expensive at inference, often requiring many discretization steps. We propose Sig-DEG (Signature-based Differential Equation Generator), a generator for distilling pre-trained diffusion models. Inspired by high-order stochastic Taylor expansions, Sig-DEG combines partial signatures that summarize Brownian motion over subintervals with a recurrent structure to approximate stochastic differential equation solutions to achieve universality. We formulate distillation as supervised learning, matching fine-resolution teacher trajectories on a coarse time grid. At inference, Sig-DEG enables fast generation, as the partial signatures can be simulated exactly from their known distributions without requiring fine-grained Brownian paths. Experiments on image and time-series generation demonstrate competitive sample quality with inference speedups of up to several hundred times over the teacher. A Schrödinger bridge example further demonstrates Sig-DEG's applicability beyond diffusion distillation.

Interest in generating realistic synthetic medical images has grown in recent years. Such datasets can mitigate the scarcity of public data for artificial intelligence research and support education. Work on synthesizing dental panoramic radiographs (PRs) has so far relied almost exclusively on generative adversarial networks (GANs), and three limitations recur: the synthesized field of view is often restricted to a cropped dentoalveolar region rather than a complete PR; observer studies of GAN-generated PRs report that clinicians still identify synthetic images with accuracies of roughly 78-82%, implying persistent visible giveaways; and adversarial training remains sensitive to instability and mode collapse. Generating a full-size PR directly at diagnostic resolution with a diffusion model is an alternative, but sampling at that resolution is costly. We therefore present PanoDiff-SR, an end-to-end two-stage pipeline developed and evaluated specifically for panoramic radiography: a denoising diffusion implicit model (PanoDiff) generates a low-resolution (LR) seed PR ($256\times128$), which a fine-tuned hybrid attention transformer (HAT) super-resolution (SR) stage upscales to a high-resolution (HR) PR of $1024\times512$. Decoupling the expensive generative step from the resolution step yields complete, full-arch PRs at diagnostic resolution on a single 47 GB GPU. The Fréchet inception distance between 7243 real and synthetic HR images is 40.5. Inception scores were 2.68, 2.38, 2.90 and 2.98 for real HR, synthetic HR, real LR and synthetic LR images, respectively. Six clinical experts, each evaluating 100 synthetic and 100 real PRs under a time limit, distinguished real from synthetic images with an average accuracy of 68.5% (50% corresponds to random guessing), substantially closer to chance than reported for GAN-based studies. Project page: https://s4nyam.github.io/panodiff/

Training data for class-conditional image synthesis often exhibit a long-tailed distribution with limited amount of images for tail classes. Such an imbalance causes mode collapse and reduces the diversity of synthesized images for tail classes. For class-conditional diffusion models trained with imbalanced data, we aim to improve the diversity and fidelity of tail class images without compromising the quality of head class images. We propose contrastive conditional-unconditional alignment (CCUA), which comprises two synergistic loss functions. Our first loss is an Alignment Loss (AL) that aligns class-conditional generation with unconditional generation at large timesteps. Alignment loss makes the denoising process insensitive to class conditions for the initial steps, which enriches tail classes through knowledge sharing from head classes. Secondly, we diversify unconditional generation via an Unsupervised Contrastive Loss (UCL) to increase the distance/dissimilarity among synthetic images. We combine the two losses to implicitly diversify conditional generation. Our framework is easy to implement as demonstrated on both U-Net based architecture and Diffusion Transformer. Our method outperforms vanilla denoising diffusion probabilistic models, score-based diffusion model, and alternative contrastive methods for class-imbalanced image generation across various datasets, in particular ImageNet-LT with 256$\times$256 resolution.

Texture map production is an important part of 3D modeling and determines the rendering quality. Recently, diffusion-based methods have opened a new way for texture generation. However, restricted control flexibility and limited prompt modalities may prevent creators from producing desired results. Furthermore, inconsistencies between generated multi-view images often lead to poor texture generation quality. To address these issues, we introduce FlexPainter, a novel texture generation pipeline that enables flexible multi-modal conditional guidance and achieves highly consistent texture generation. A shared conditional embedding space is constructed to perform flexible aggregation between different input modalities. Utilizing such embedding space, we present an image-based CFG method to decompose structural and style information, achieving reference image-based stylization. Leveraging the 3D knowledge within the image diffusion prior, we first generate multi-view images simultaneously using a grid representation to enhance global understanding. Meanwhile, we propose a view synchronization and adaptive weighting module during diffusion sampling to further ensure local consistency. Finally, a 3D-aware texture completion model combined with a texture enhancement model is used to generate seamless, high-resolution texture maps. Comprehensive experiments demonstrate that our framework significantly outperforms state-of-the-art methods in both flexibility and generation quality.

Quantum Diffusion Models (QDMs) are an emerging paradigm in Generative AI that aims to use quantum properties to improve the performances of their classical counterparts. However, existing algorithms are not easily scalable due to the limitations of near-term quantum devices. Following our previous work on QDMs, here we propose and implement two physics-inspired protocols. In the first, we use the formalism of quantum stochastic walks, showing that a specific interplay of quantum and classical dynamics in the forward process produces statistically more robust models generating sets of MNIST images with lower Fréchet Inception Distance (FID) than using totally classical dynamics. In the second approach, we realize an algorithm to generate images by exploiting the intrinsic noise of real IBM quantum hardware with only four qubits. Our work could be a starting point to pave the way for new scenarios for large-scale algorithms in quantum Generative AI, where quantum noise is neither mitigated nor corrected, but instead exploited as a useful resource.

Nature is infinitely resolution-free. In the context of this reality, existing diffusion models, such as Diffusion Transformers, often face challenges when processing image resolutions outside of their trained domain. To address this limitation, we conceptualize images as sequences of tokens with dynamic sizes, rather than traditional methods that perceive images as fixed-resolution grids. This perspective enables a flexible training strategy that seamlessly accommodates various aspect ratios during both training and inference, thus promoting resolution generalization and eliminating biases introduced by image cropping. On this basis, we present the Flexible Vision Transformer (FiT), a transformer architecture specifically designed for generating images with unrestricted resolutions and aspect ratios. We further upgrade the FiT to FiTv2 with several innovative designs, includingthe Query-Key vector normalization, the AdaLN-LoRA module, a rectified flow scheduler, and a Logit-Normal sampler. Enhanced by a meticulously adjusted network structure, FiTv2 exhibits $2\times$ convergence speed of FiT. When incorporating advanced training-free extrapolation techniques, FiTv2 demonstrates remarkable adaptability in both resolution extrapolation and diverse resolution generation. Additionally, our exploration of the scalability of the FiTv2 model reveals that larger models exhibit better computational efficiency. Furthermore, we introduce an efficient post-training strategy to adapt a pre-trained model for the high-resolution generation. Comprehensive experiments demonstrate the exceptional performance of FiTv2 across a broad range of resolutions. We have released all the codes and models at https://github.com/whlzy/FiT to promote the exploration of diffusion transformer models for arbitrary-resolution image generation.

Score-based Generative Models (SGMs) have achieved remarkable success in generation tasks by establishing a diffusion process that gradually perturbs real data into Gaussian noise and then learning a reverse process to reconstruct the data from noise. However, conventional denoising methods, such as Langevin dynamics and numerical stochastic differential equation solvers, rely on randomness but suffer from slow generation speeds due to the high number of score function evaluations. To address this, we propose a plug-and-play Markov adaptive momentum sampling method, inspired by the strong connection between the SGMs' sampling process and stochastic gradient descent optimization. Our approach accelerates the transformation process without introducing additional hyperparameters. Theoretically, we establish a rigorous foundation by analyzing the relationship between the distribution of samples generated by our method and the original data distribution. This provides a novel perspective on the analysis of sampling distributions. Empirically, our method demonstrates superior efficiency, generating high-quality images/graphs in significantly fewer sampling steps, achieving a speedup of 2x to 5x while maintaining or surpassing baseline performance on various image and graph generation benchmarks. These results underscore the effectiveness of adaptive momentum in enhancing the efficiency of SGMs.