Latent Diffusion Models (LDMs) have become a cornerstone for zero-shot style transfer in multimedia content creation, but they frequently struggle with a critical trade-off between artistic stylization fidelity and semantic structural preservation. A key oversight in existing methods is the neglect of frequency-domain distinctions in visual signals, which leads to prevalent issues like content drift and style leakage. To address these limitations, we propose FreSCo, a novel training-free framework that explicitly decouples content and style through dual-domain control mechanisms. First, the Dynamic Wavelet Latent Fusion (DWLF) module decomposes latent features via Discrete Wavelet Transform (DWT), injecting style exclusively into high-frequency texture sub-bands while boosting spectral energy to counteract VAE-induced smoothing. Second, the VAE-Compressed Masking strategy encodes edge maps directly into the latent space, resolving pixel-latent misalignment for precise spatial control. We construct a comprehensive benchmark with 1,280 content-style pairs to rigorously evaluate performance. Extensive experiments demonstrate that FreSCo achieves state-of-the-art results, generating high-fidelity artistic textures while maintaining superior structural consistency across diverse multimedia content creation scenarios compared to existing baselines.

Deep learning models have achieved remarkable progress in precipitation prediction. However, they still face significant challenges in accurately capturing spatial details of radar images, particularly in regions of high precipitation intensity. This limitation results in reduced spatial localization accuracy when predicting radar echo images across varying precipitation intensities. To address this challenge, we propose an innovative precipitation prediction approach termed the Multi- Task Latent Diffusion Model (MTLDM). The core idea of MTLDM lies in the recognition that precipitation radar images represent a combination of multiple components, each corresponding to different precipitation intensities. Thus, we adopt a divide-and-conquer strategy, decomposing radar images into several sub-images based on their precipitation intensities and individually modeling these components. During the prediction stage, MTLDM integrates these sub-image representations by utilizing a trained latent-space rainfall diffusion model, followed by decoding through a multi-task decoder to produce the final precipitation prediction. Experimental evaluations conducted on the MRMS dataset demonstrate that the proposed MTLDM method surpasses state-of-the-art techniques, achieving a Critical Success Index (CSI) improvement of 13-26%.

Deterministic deep learning models for precipitation nowcasting often face several limitations, including cumulative error in long-sequence predictions, over-smoothing, and a reduced ability to capture rare, high-impact rainfall due to data imbalance. To address these challenges, we propose the stagewise scheduled rainfall forecasting network (SSRF-Net), a convolutional framework for continuous multistep rainfall prediction that achieves lower floating-point operations (FLOPs) than competitive baselines under a standardized evaluation. Our framework introduces a multistage, sliding-window prediction mechanism trained with teacher forcing and scheduled sampling to mitigate error accumulation and stabilize training. We design an asymmetric encoder–decoder (E–D) architecture featuring a differential selective encoder (DSE) for selective feature compression and an additive fusion decoder (AFD) that progressively reconstructs details and alleviates over-smoothing. We further introduce an intensity-weighted Gaussian KL divergence loss that aligns sequence-level Gaussian summaries (means and variances) of predictions and ground truth via a KL term, prioritizing heavy-rain events without assuming pixelwise Gaussianity. Extensive experiments on the KNMI and SEVIR datasets show that SSRF-Net outperforms strong baselines, particularly for moderate to severe precipitation; on KNMI, it yields up to 41.8% higher per-frame critical success index (CSI) at the 30-mm/h threshold, with consistent gains on SEVIR.

Deep neural networks have made great achievements in rainfall prediction.However, the current forecasting methods have certain limitations, such as with blurry generated images and incorrect spatial positions. To overcome these challenges, we propose a Two-stage Rainfall-Forecasting Diffusion Model (TRDM) aimed at improving the accuracy of long-term rainfall forecasts and addressing the imbalance in performance between temporal and spatial modeling. TRDM is a two-stage method for rainfall prediction tasks. The task of the first stage is to capture robust temporal information while preserving spatial information under low-resolution conditions. The task of the second stage is to reconstruct the low-resolution images generated in the first stage into high-resolution images. We demonstrate state-of-the-art results on the MRMS and Swedish radar datasets. On the Swedish dataset, our proposed method achieves a 5-10 percentage-point improvement in CSI compared to the other baseline methods for the 60-80 minute prediction range. Our project is open source and available on GitHub at: https://github.com/clearlyzerolxd/TRDM.

Short-term precipitation forecasting remains challenging due to the difficulty in capturing long-term spatiotemporal dependencies. Current deep learning methods fall short in establishing effective dependencies between conditions and forecast results, while also lacking interpretability. To address this issue, we propose a precipitation nowcasting using a diffusion transformer with causal attention (DTCA) model. Our model leverages the transformer and combines causal attention mechanisms to establish spatiotemporal queries between conditional information (causes) and forecast results (results). This design enables the model to effectively capture long-term dependencies, allowing forecast results to maintain strong causal relationships with input conditions over a wide range of time and space. We explore four variants of spatiotemporal information interactions for DTCA, demonstrating that global spatiotemporal labeling interactions yield the best performance. In addition, we introduce a channel-to-batch shift (CTBS) operation to further enhance the model’s ability to represent complex rainfall dynamics. We conducted experiments on two datasets. Compared to state-of-the-art U-Net-based methods, our approach improved the critical success index (CSI) for predicting heavy precipitation by approximately 15% and 8%, respectively, achieving state-of-the-art performance. Our project is open source and available on GitHub at:https://github.com/ybu-lxd/DTCA.

The growing volume of meteorological data and advancements in computing performance have made the application of deep learning technology in short-term rainfall prediction crucial. However, existing learning approaches struggle to accurately predict detailed spatial location information, particularly obvious in predicting extreme rainfall events, leading to inadequate prediction accuracy and subpar performance in meteorological assessment indicators, limiting the effectiveness and applicability of deep learning models in rainfall prediction. To address these challenges, we propose a spacetime separable latent diffusion model with intensity structure information (SSLDM-ISI) to capture spatial and temporal information more efficiently. SSLDM-ISI incorporates two key strategies to solve the spatiotemporal information issue. First, a spatiotemporal conversion block (STC Block) within the backbone network effectively extracts and integrates spatiotemporal information. Second, our proposed latent space coding technique based on rainfall intensity structural information enhances the information representation ability of extreme rainfall. In addition, an examination of the impact of various conditions is conducted on the prediction results to enhance the model’s prediction accuracy and stability. Through comparative analysis of meteorological evaluation and image quality evaluation indicators on two datasets, our proposed approach outperforms existing advanced technologies in short-term rainfall prediction, achieving current state-of-the-art results. Our project is open source and available on GitHub at:https://github.com/ybu-lxd/SISLDM-ISI