Text & Image to Video
Generate a video and audio from a text prompt with optional image, last-frame, and audio references.
Prompt Image
Click/drag to upload
Last Image
Click/drag to upload
Prompt Audio
Click/drag to upload
Prompt *
Prompt text used to generate the video and audio.
Resolution
Target output resolution preset.
Number of Frames
Number of generated video frames when prompt audio is not set.
Inference Steps
Number of diffusion inference steps.
Seed
Random seed. Use -1 to let the pipeline choose one.
Height
Optional explicit output height.
Width
Optional explicit output width.
Select model
Preview
No result yet
Preview the task result before downloading or chaining it into other flows.
Text & Image to Video
mcp_tool_id
remote_mcp_endpoint
https://medux.io/api/mcp/v1Invocation Example
Generate a video and audio from a text prompt with optional image, last-frame, and audio references.