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

powered by ByteDance AI

Prompt

Describe the scene and motion to generate.

Resolution

The resolution of the generated video.

480p

Duration

The duration of the video in seconds

Aspect ratio

The aspect ratio of the video

Auto

Generate audio

Generate synchronized audio together with the video.

Yes

This is a SFW (Safe For Work) only model.