# Temporal Consistency

Project Starlight is an AI video enhancement model launched by Topaz Labs, designed to improve the quality of low-resolution and damaged videos. It uses diffusion model technology to achieve video super-resolution, noise reduction, deblurring, and sharpening, while maintaining temporal consistency to ensure smooth transitions between video frames. This technology is a significant breakthrough in the field of video enhancement, bringing unprecedented high-quality results to video repair and enhancement. Currently, Project Starlight offers a free trial and plans to support 4K export in the future, primarily targeting users and enterprises who need high-quality video repair and enhancement.

ViViD is a new framework for video virtual try-on based on diffusion models. It designs a clothing encoder to extract fine-grained clothing semantic features, and introduces a lightweight pose encoder to ensure temporal consistency, generating realistic video try-on effects. ViViD has collected the largest-scale, most diverse clothing types, and highest resolution video virtual try-on dataset to date.

Slicedit is a zero-shot video editing technique that utilizes text-to-image diffusion models coupled with spatiotemporal slicing to enhance temporal consistency in video editing. This technology preserves the original video's structure and motion while adhering to the target text description. Extensive experiments have demonstrated Slicedit's significant advantages in editing real-world videos.

StreamingT2V is an advanced autoregressive technique that creates long videos with rich, dynamic motion without any stuttering. It ensures temporal consistency within the video, aligning closely with the descriptive text, and maintains high-frame-rate image quality.

FlowVid is an optical flow guided video synthesis model. By utilizing the spatial and temporal information of optical flow, it achieves temporal consistency between video frames. It seamlessly integrates with existing image synthesis models to enable various modification operations, including stylization, object swapping, and local editing. FlowVid boasts fast generation speed; a 4-second, 30FPS, 512×512 resolution video can be generated in just 1.5 minutes, outperforming CoDeF (3.1x), Rerender (7.2x), and TokenFlow (10.5x) respectively. In user evaluations, FlowVid achieved a quality score of 45.7%, significantly surpassing CoDeF (3.5%), Rerender (10.2%), and TokenFlow (40.4%).