These models can generate and edit videos from text prompts and images. They use advanced AI techniques like diffusion models and latent space interpolation to create high-quality, controllable video content.

Key capabilities:

• Text-to-video generation - Convert text prompts into video clips and animations. Useful for quickly prototyping video concepts.
• Image-to-video generation - Animate still images into video.
• Inpainting for infinite zoom - Use image inpainting to extrapolate video frames and create infinite zoom effects.
• Stylization - Apply artistic filters like cartoonification to give videos a unique look and feel.

State of the art: minimax/video-01

For most people looking to generate custom videos from text or image prompts, we recommend minimax/video-01, also known as Hailuo . This model supports the generation of high-definition videos at 720p resolution and 25fps, featuring cinematic camera movement effects. It can quickly create visually striking content based on text descriptions.

Open source: tencent/hunyuan-video

The Hunyuan Video model by Tencent 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.