Person image generation has become an increasingly important problem in computer vision with broad applications in virtual try-on, digital content creation, entertainment, and human-computer interaction. Despite recent advances in diffusion-based generative models that can produce photorealistic results, existing pipelines are still constrained by rigid modality requirements. Most prior methods rely on fixed patterns such as pose-plus-appearance inputs or text-only descriptions, limiting their flexibility and controllability in practical scenarios where users may prefer different or mixed types of guidance. This lack of adaptability poses a clear barrier to deployment in real-world systems. To overcome these challenges, we propose MaPPA (Multimodal Controllable Person Image Generation with Pose and Appearance Guidance), a unified multimodal framework that leverages transformer-based latent diffusion models. The central idea is to provide composable control over multiple modalities, enabling person image generation conditioned on text prompts, reference appearance images, pose keypoints, or any combination thereof. To achieve this, we introduce a unified framework that incorporates dedicated control blocks for appearance and pose guidance, which are strategically interleaved with transformer base blocks. These control blocks are conditioned on a unified multimodal embedding that integrates heterogeneous inputs into a consistent representation, thereby supporting arbitrary modality combinations with a single unified pipeline. Another key contribution of MaPPA is a cumulative classifier-free guidance strategy that enables allowing users to independently adjust the strength of appearance and pose guidance via scalar weights from different control signals. This design allows users to adjust the relative strength of appearance versus pose guidance, providing fine-grained controllability during inference. Furthermore, to address the common problem of detail loss in latent-diffusion decoders, we propose a texture enhancement decoding (TED) strategy, which fine-tunes the VAE decoder with edge-aware reconstruction objectives. This refinement significantly alleviates texture distortion, preserving high-frequency details in clothing patterns, facial regions, and other fine structures. Extensive experiments confirm that MaPPA achieves competitive quantitative scores while providing superior perceptual quality and user preference. Unlike task-specific methods, our framework-though constrained by the capacity of the unified multimodal embedding-supports combinations of text, pose, and appearance modalities within a single pipeline, demonstrating both flexibility and practical value. The code and the corresponding model will be made publicly available to the research community.

To advance real-world fashion image editing, we analyze existing two-stage pipelines(mask generation followed by diffusion-based editing)which overly prioritize generator optimization while neglecting mask controllability. This results in two critical limitations: I) poor user-defined flexibility (coarse-grained human masks restrict edits to predefined regions like upper torso; fine-grained clothes masks preserve poses but forbid style/length customization). II) weak pose robustness (mask generators fail due to articulated poses and miss rare regions like waist, while human parsers remain limited by predefined categories). To address these gaps, we propose Pose-Star, a framework that dynamically recomposes body structures (e.g., neck, chest, etc.) into anatomy-aware masks (e.g., chest-length) for user-defined edits. In Pose-Star, we calibrate diffusion-derived attention (Star tokens) via skeletal keypoints to enhance rare structure localization in complex poses, suppress noise through phase-aware analysis of attention dynamics (Convergence,Stabilization,Divergence) with threshold masking and sliding-window fusion, and refine edges via cross-self attention merging and Canny alignment. This work bridges controlled benchmarks and open-world demands, pioneering anatomy-aware, pose-robust editing and laying the foundation for industrial fashion image editing.

Currently, unsupervised industrial anomaly detection and anomaly localization based on deep learning have achieved great success. The most commonly used dataset for industrial anomaly detection and anomaly localization is MV-TAD, and the most commonly used evaluation metric is AUROC. Most research methods are based on the above datasets and experiment evaluation metrics. Although the most advanced method has nearly 100% AUROC index values in the above dataset, the results are still not ideal, as seen by observing the anomaly segmentation maps after the experiments. Therefore, in this paper, we use a new metric, F1-measure, to evaluate the experimental performance of industrial anomaly detection and anomaly localization models. Compared with the AUROC metric, the F1-measure ensures complete and accurate detection by reconciling Precision and Recall. We use ResNet34 and WideRes-Net101 pre-trained encoders based on the current state-of-the-art normalized flow-based generative model anomaly detection method to train and test on the dataset, and achieve good experimental performance. In addition to MVTAD, we extended the dataset to DAGM 2007, BTAD, trained and tested them. Furthermore, we use the new evaluation metric, F1-measure, to evaluate the experimental results.