Collections

Generate 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.

Featured models

wan-videowan-video/wan-2.5-i2v

Alibaba Wan 2.5 Image to video generation with background audio

Updated 3 weeks, 6 days ago

142.2K runs

Official
veo-3.1-fast
googlegoogle/veo-3.1-fast

New and improved version of Veo 3 Fast, with higher-fidelity video, context-aware audio and last frame support

Updated 1 month ago

199.4K runs

Official
googlegoogle/veo-3.1

New and improved version of Veo 3, with higher-fidelity video, context-aware audio, reference image and last frame support

Updated 1 month ago

243.6K runs

Official
bytedancebytedance/seedance-1-pro-fast

A faster and cheaper version of Seedance 1 Pro

Updated 1 month, 3 weeks ago

390.2K runs

Official
kwaivgikwaivgi/kling-v2.5-turbo-pro

Kling 2.5 Turbo Pro: Unlock pro-level text-to-video and image-to-video creation with smooth motion, cinematic depth, and remarkable prompt adherence.

Updated 1 month, 3 weeks ago

1.5M runs

Official
wan-videowan-video/wan-2.5-i2v-fast

Wan 2.5 image-to-video, optimized for speed

Updated 1 month, 3 weeks ago

40.8K runs

Official
minimaxminimax/hailuo-2.3

A high-fidelity video generation model optimized for realistic human motion, cinematic VFX, expressive characters, and strong prompt and style adherence across both text-to-video and image-to-video workflows

Updated 1 month, 3 weeks ago

31.2K runs

Official
minimaxminimax/hailuo-2.3-fast

A lower-latency image-to-video version of Hailuo 2.3 that preserves core motion quality, visual consistency, and stylization performance while enabling faster iteration cycles.

Updated 1 month, 3 weeks ago

24.9K runs

Official

Recommended Models

AltStyle によって変換されたページ (->オリジナル) /