The video generator works in two modes. "Photo to Video" brings an uploaded image to life: a person smiles and turns their head, waves roll onto the shore, the camera glides around the scene. "Text to Video" creates a clip from scratch based on your description — characters, setting, camera movement and mood. Most models generate sound right away too: speech, music and ambient noise.
All the leading video models of 2026 are available in one interface. MiniMax H3 Turbo is the fastest and most affordable, producing a clip in about a minute. MiniMax H3 is the leader for animating portraits. Kling 3 and Kling 3 Pro deliver cinematic camera movement and lighting. Google's Veo 3.1 offers realistic physics. Gemini Omni Flash is Google's newest model, with precise prompt following and speech. Alibaba's Wan 3.0 excels at building narrative scenes with multiple shot changes.
Duration is 5 or 10 seconds (4–8 seconds for Veo 3.1), resolution is 720p or 1080p, in 16:9, 9:16 and 1:1 formats. Generation happens in the cloud — no graphics card or software needed. The finished MP4 can be extended, upscaled to 4K, or published right away.