EvTexture is an event-based, vision-driven video super-resolution (VSR) technology that leverages high-frequency details in event signals to better recover texture regions in VSR. This technique uniquely proposes using event signals for texture enhancement. It iteratively refines texture regions by exploring high temporal resolution event information through a texture enhancement module, achieving more accurate and richer high-resolution details. On four datasets, EvTexture has achieved state-of-the-art performance, particularly on the Vid4 dataset, where it can achieve a gain of up to 4.67dB compared to recent event-based methods.

I2VEdit is an innovative video editing technology that extends the editing of a single frame to the entire video through a pre-trained image-to-video model. This technology can adaptively maintain the visual and motion integrity of the source video and effectively handle global editing, local editing, and moderate shape changes, which existing methods cannot achieve. The core of I2VEdit includes two main processes: rough motion extraction and appearance refinement, which are precisely adjusted through coarse-grained attention matching. In addition, a skip interval strategy is introduced to mitigate the quality degradation in the automatic regression generation process of multiple video segments. Experimental results show that I2VEdit's superior performance in fine-grained video editing demonstrates its ability to produce high-quality, temporally consistent output.

FunClip is a fully open-source, locally deployed automated video editing tool. It utilizes the FunASR Paraformer series of open-source models from Alibaba's TGETHER Lab for video voice recognition. Users can then freely select text segments or speakers from the recognized results, and clicking the crop button retrieves the corresponding video clip. FunClip integrates Alibaba's open-source industrial-grade Paraformer-Large model, one of the best-performing open-source Chinese ASR models currently available, and accurately predicts timestamps in an integrated manner.

VideoGigaGAN is a video super-resolution (VSR) model based on the large-scale image upsampler GigaGAN. It can generate videos with high-frequency details and temporal consistency. The model significantly improves temporal consistency by adding temporal attention layers and feature propagation modules, and utilizes anti-aliasing blocks to reduce the jaggies effect. VideoGigaGAN has been compared with state-of-the-art VSR models on public datasets and demonstrated 8x super-resolution video results.

The Sieve Eye Contact Correction API is a fast and high-quality solution designed for developers, enabling eye contact correction in videos. This technology redirects eye gaze, allowing video subjects to simulate eye contact with the camera even when not directly facing it. It supports various customization options to fine-tune eye gaze redirection while preserving natural blinking and head movements, and introduces a random 'look away' feature to prevent a fixed gaze. Additionally, it offers split-screen views and visualization options for easy debugging and analysis. This API is primarily aimed at video creators, online education providers, and anyone looking to enhance video communication quality. The pricing is $0.10 per minute of video.

EvTexture is an event-based, vision-driven video super-resolution (VSR) technology that leverages high-frequency details in event signals to better recover texture regions in VSR. This technique uniquely proposes using event signals for texture enhancement. It iteratively refines texture regions by exploring high temporal resolution event information through a texture enhancement module, achieving more accurate and richer high-resolution details. On four datasets, EvTexture has achieved state-of-the-art performance, particularly on the Vid4 dataset, where it can achieve a gain of up to 4.67dB compared to recent event-based methods.

Developed by Kuaishou, KuaiYing is a video editing application that offers a comprehensive suite of video editing features, including cutting, audio, subtitles, special effects, and more. It aims to help users easily create engaging and professional video content. It features an AI-powered anime video function that can transform videos into anime styles, offering various options like anime style, national style, and Japanese anime style. Additionally, KuaiYing boasts AI creation tools such as AI drawing, AI text-to-image, and an AI copywriting library to assist users in their creative endeavors. KuaiYing also provides a creative center to help users view data, find inspiration, and offers a powerful resource library including stickers and trending content to enhance user engagement.

Underlord is an AI-driven video and podcast editing assistant within the Descript platform. It simplifies the video and audio content editing process through a series of intelligent editing tools, boosting both productivity and quality. Underlord is committed to making creative work smoother with AI technology while minimizing the tediousness of post-production editing.

I2VEdit is an innovative video editing technology that extends the editing of a single frame to the entire video through a pre-trained image-to-video model. This technology can adaptively maintain the visual and motion integrity of the source video and effectively handle global editing, local editing, and moderate shape changes, which existing methods cannot achieve. The core of I2VEdit includes two main processes: rough motion extraction and appearance refinement, which are precisely adjusted through coarse-grained attention matching. In addition, a skip interval strategy is introduced to mitigate the quality degradation in the automatic regression generation process of multiple video segments. Experimental results show that I2VEdit's superior performance in fine-grained video editing demonstrates its ability to produce high-quality, temporally consistent output.

FunClip is a fully open-source, locally deployed automated video editing tool. It utilizes the FunASR Paraformer series of open-source models from Alibaba's TGETHER Lab for video voice recognition. Users can then freely select text segments or speakers from the recognized results, and clicking the crop button retrieves the corresponding video clip. FunClip integrates Alibaba's open-source industrial-grade Paraformer-Large model, one of the best-performing open-source Chinese ASR models currently available, and accurately predicts timestamps in an integrated manner.

VideoGigaGAN is a video super-resolution (VSR) model based on the large-scale image upsampler GigaGAN. It can generate videos with high-frequency details and temporal consistency. The model significantly improves temporal consistency by adding temporal attention layers and feature propagation modules, and utilizes anti-aliasing blocks to reduce the jaggies effect. VideoGigaGAN has been compared with state-of-the-art VSR models on public datasets and demonstrated 8x super-resolution video results.

Adobe Premiere Pro is a powerful video editing software that integrates AI technology to simplify complex editing tasks and accelerate the editing process. The software provides features such as text-based editing, AI-powered audio classification, speech-to-text, voice enhancement, scene detection, auto-color adjustment, shape transformation, color matching, automatic audio adjustment, and automatic reconstruction, significantly improving editing efficiency and creative possibilities. Premiere Pro is suitable for editing everything from social media short videos to feature films, helping users save time and focus on creativity and storytelling. Later this year, Adobe Premiere Pro plans to introduce third-party AI model functionality, enabling editors to choose the models that best suit their footage and enhancing the editing experience. These AI models include Sora from OpenAI, Runway AI's video models, and Pika's video models. Furthermore, Premiere Pro will offer content verification features to help users understand whether they have used AI and which model was used in their media creation.