Generate Videos from Text
Describe the subject, action, setting, lighting, and camera movement to create a new video from a prompt.
MiniMax H3 for Android
Create 4–15 second AI videos from text, frames, and multimodal references. Guide motion, camera, and visual style with output up to 2K.
Create with MiniMax H3
Start with a prompt, guide the first and last frames, or add multimodal references to create videos with more control over motion, camera, and style.
Describe the subject, action, setting, lighting, and camera movement to create a new video from a prompt.
Add a starting frame, an ending frame, or both to guide how your video begins and ends.
Use supported images, video, and audio references to guide subjects, motion, camera direction, and visual style.
Describe subject movement, pans, zooms, tracking shots, and other camera behavior in your prompt.
Choose a duration from 4 to 15 seconds and generate the final video in 768P or 2K.
Review your settings, generate the video, and save the finished result from your account.
Four-step workflow
Install the Android app, choose a workflow, add your prompt and references, then customize the settings and generate your video.
Open the MiniMax H3 listing on Google Play and install the Android app.
Select text-to-video, image-to-video, frame-controlled, or reference-based generation.
Describe the video you want and add supported reference media when you need more control.
Choose a 4–15 second duration and 768P or 2K, then generate and download the result.
Download the MiniMax H3 app from Google Play, or open the browser generator to start creating online.