Videos from images

These models can generate videos from images. They use advanced AI techniques like diffusion models and latent space interpolation to create high-quality, controllable video content from an image or starting frame

Key capabilities:

• Image-to-video generation - Animate still images into video.
• Transfer style - Modify a video with a starting image that will guide the video modification.
• Start and end frame - Create a video with a start and end image.

Open source: wan-video

The Wan video models model by Wan-AI is an excellent open-source option, competitive with the best proprietary video models. Try adjusting the number of steps used for each frame to trade off between generation speed and detail.

Other rankings

Generative video is a rapidly advancing field. Check out the arena and leaderboard at Artificial Analysis to see what’s popular today.