# High-resolution video generation

Cosmos-Predict2 is a series of high-performance pre-trained world foundation models designed to generate physics-aware images, videos, and world states, which can be used for the development of physics AI.

Wan 2.1 is a comprehensive open-source video foundation model designed to push the boundaries of video generation, supporting tasks such as text-to-video and image-to-video generation.

CogVideoX is an open-source video generation model that supports generating videos from images, similar to the Qingying platform.

The first DiT-based video generation model capable of real-time generation of high-quality videos, supporting two scenarios: text-to-video and image + text-to-video.

An improved video generation tool based on the CogVideoX architecture, supporting text/image generation of approximately 6-second, 8fps videos

A video generation model based on the improved CogVideoX architecture, supporting text/image-to-video and multi-resolution generation

The first open-source 1024x576 text-to-video model, fine-tuned from a base model