Video models

​

Google

• Veo 3.1 — Google’s frontier video model. Supports text-to-video, image-to-video, reference-to-video, and first-and-last-frame.

​

OpenAI

• Sora 2 — text-to-video and image-to-video.

​

xAI

• Grok Imagine Video — text-to-video, image-to-video, and video-to-video.
• Grok Imagine Video Extend — extend an existing clip.

​

Kuaishou (Kling)

• Kling 3.0 Omni — text-to-video, image-to-video, reference-to-video.
• Kling 3 Pro
• Kling 2.6 Pro
• Kling 2.5 Turbo
• Kling Lipsync — sync an existing video to a new audio track.
• Kling Avatar — animate a still image as a talking avatar.

​

ByteDance

• Seedance 2.0 — text-to-video, image-to-video, reference-to-video, video-to-video.

​

Alibaba

• Wan 2.7 — text-to-video, image-to-video, reference-to-video, video-to-video.
• Wan 2.2 — text-to-video, image-to-video.
• Happy Horse 1.0 — text-to-video, image-to-video, video-to-video. A reference-based variant is also available.

​

Lightricks

• LTX 2.3 — text-to-video and image-to-video.
• LTX 2.3 (Audio to video) — image-to-video driven by an audio track.

​

Vidu

• Vidu Q3 — text-to-video and image-to-video.

​

PixVerse

• PixVerse v5.6 — text-to-video and image-to-video.

​

Lipsync & avatar

• Infinitalk — talking-head animation from an image plus audio.
• AI Avatar — image-to-video avatar animation.
• Sync Lipsync v3 and Sync Lipsync v2 Pro — sync video to a new audio track.