Generative models have shown encouraging results for time series anomaly identification in the past few years. However, real-world time series data often presents inherent spatiotemporal uncertainties caused by noise and non-stationary environmental factors in sensor measurements. Moreover, there is a significant amount of redundant information association between various dimensions of data attributes. Existing approaches are unable to dynamically capture critical features and suppress noise interference in complex conditions like network-traffic, where the importance of each individual dimension in the temporal features often evolves dynamically over time. To solve these problems, we present Diff-DTF, a brand-new anomaly detection approach integrating diffusion models with dynamic dimension-aware mechanisms. Our method proposes a dynamic temporal feature extraction mechanism that adaptively allocates dimension-wise weights based on the temporal characteristics of the dataset to achieve dynamic focus on critical features. Furthermore, we creatively integrate depthwise separable convolution (DWConv) and partial convolution (PConv) to enhance information transmission. This allows our model to refine important information by adaptively emphasizing the most critical temporal characteristics. Diff-DTF significantly enhances the detection of anomalies in multivariate time series through an effective integration of diffusion models with dynamic temporal feature extraction and refinement processes. Comprehensive evaluations across four real-world time series datasets reveal significant performance gains over existing baseline methods, validating its effectiveness in detecting anomalies within complex multivariate time series data.