In recent years, the research of image inpainting based on deep learning has made a lot of remarkable progress. However, when there is a large area mask, due to the lack of reasonable prior information guidance, the repair results often appear artifacts and blurred textures. Therefore, based on this problem, we propose an image inpainting algorithm that combines prior features with image predictive filtering. It consists of two branches: image filtering kernel prediction branch, feature inference and image filtering branch. The features are extracted from the decoder part of the image filter kernel prediction branch. The multi-scale external spatial feature fusion is used to reconstruct the mask region features, and the decoding stage is passed to another branch as a prior feature to provide richer semantic information for image inpainting. Then, a spatial feature-aware inference block is introduced in the feature inference and image filtering branches, which can filter out the distracting features and capture the informative long-distance image context for inference. In the final stage, the image prediction filter kernel is used to filter and eliminate artifacts. Compared with other repair networks on CelebA and Places2 datasets, the superiority of this method in repair quality is proved.