StreamV2V is a diffusion model that achieves real-time video-to-video (V2V) translation through user prompts. Unlike traditional batch processing methods, StreamV2V employs a streaming approach, capable of handling infinite-frame videos. Its core mechanism involves a feature library that stores information from past frames. For incoming frames, StreamV2V utilizes extended self-attention and direct feature fusion techniques to directly integrate similar past features into the output. The feature library is continuously updated by merging stored and new features, ensuring it remains concise and information-rich. StreamV2V stands out for its adaptability and efficiency, seamlessly integrating with image diffusion models without requiring fine-tuning.