Three new video model families are now available for text-to-video and image-to-video:
- MiniMax H3: native generation up to 768P, with 2K and 4K upscale options. [Text-to-Video] [Image-to-Video]
- Seedance 2.5: synchronized audio, first/last-frame guidance, and clips up to 30 seconds. [Text-to-Video] [Image-to-Video]
- FLUX.3: synchronized audio and flexible 5-20 second generation at 720p or 1080p. [Text-to-Video] [Image-to-Video]

Generate a video from a text description

Processing time: ~1-8 min

powered by MiniMax AI

Prompt

Describe the scene and motion to generate.

Duration

The duration of the video in seconds

Resolution

The resolution of the generated video.

480P

Aspect ratio

The aspect ratio of the generated video.

16:9

More options

Seed

Unique output seed number. If not provided, the output will be random.

Enable prompt expansion

Expand the prompt before generating the video.

Yes