Jul 28, 2025 · Wan: Open and Advanced Large-Scale Video Generative Models We are excited to introduce Wan2.2, a major upgrade to our foundational video models. With Wan2.2, we have focused on incorporating the following innovations: 👍 Effective MoE Architecture: Wan2.2 introduces a Mixture-of-Experts (MoE) architecture into video diffusion models. By separating the denoising process cross timesteps with Jun 20, 2025 · Official SeedVR2 Video Upscaler for ComfyUI. Contribute to numz/ComfyUI-SeedVR2_VideoUpscaler development by creating an account on GitHub. Feb 23, 2025 · Video-R1 significantly outperforms previous models across most benchmarks. Notably, on VSI-Bench, which focuses on spatial reasoning in videos, Video-R1-7B achieves a new state-of-the-art accuracy of 35.8%, surpassing GPT-4o, a proprietary model, while using only 32 frames and 7B parameters. This highlights the necessity of explicit reasoning capability in solving video tasks, and confirms the VisoMaster is a powerful yet easy-to-use tool for face swapping and editing in images and videos. It utilizes AI to produce natural-looking results with minimal effort, making it ideal for both casual users and professionals. A machine learning-based video super resolution and frame interpolation framework. Est. Hack the Valley II, 2018. - k4yt3x/video2x LTX-Video is the first DiT-based video generation model that can generate high-quality videos in real-time. It can generate 30 FPS videos at 1216×704 resolution, faster than it takes to watch them. The model is trained on a large-scale dataset of diverse videos and can generate high-resolution videos with realistic and diverse content. The model supports image-to-video, keyframe-based yt-dlp is a feature-rich command-line audio/video downloader with support for thousands of sites. The project is a fork of youtube-dl based on the now inactive youtube-dlc. INSTALLATION Detailed instructions Release Files Update Dependencies Compile USAGE AND OPTIONS

General Options Network Options Geo-restriction Video Selection Download Options TTT-Video TTT-Video is a repository for finetuning diffusion transformers for style transfer and context extension. We use Test-Time Training (TTT) layers to handle long-range relationships across the global context, while reusing the original pretrained model's attention layers for local attention on each three second segment. Contribute to kijai/ComfyUI-WanVideoWrapper development by creating an account on GitHub. Introduced a novel taxonomy for Vid-LLMs based on video representation and LLM functionality. Added a Preliminary chapter, reclassifying video understanding tasks from the perspectives of granularity and language involvement, and enhanced the LLM Background section.