Wan 2.6

Google

Veo 3.1 is Google's flagship video model on MagicShot. It generates cinematic clips with native audio — dialogue, ambient sound and effects rendered together with the footage — and handles camera direction like pans, dollies and drone moves from a plain-language prompt. Use it through Text to Video or Image to Video when you want the most film-like motion available.

Kuaishou

Unified multimodal video generation with reference images and video editing.

ByteDance

Accepts multiple reference inputs including images, videos and audio.

PixVerse

PixVerse V6 generates cinematic 1080p videos with synchronized native audio from a single text prompt or image, combining multi-shot storytelling, 20 professional lens controls, stable character consistency across scenes, and flexible 16:9, 9:16, or 1:1 output for social media, ads, and film-quality productions.

Happy Horse 1.0 is an AI video generator that turns text prompts and images into smooth, high-quality animated video with vivid motion, character consistency, and flexible aspect ratios for social media, ads, and creative projects.

Kling 3.0 Omni is an AI video generator that turns text prompts and images into cinematic 1080p video with native audio, Motion Brush control, camera motion presets, and subject consistency across every frame.