Put the subject and action first
Search-like keyword lists do not direct motion well. Start with who or what is on screen and what changes during the shot.
MiniMax H3 Text to Video Generator
Turn a written shot brief into a 2K AI video. Direct the subject, action, setting, camera, light, pacing, and sound in one focused prompt—no source image required.
ReferenceFramesFirst & Last FrameTextText to Video
ImagesAdd reference images0/9up to 9JPG/PNG/WebP · up to 9
VideosAdd reference videos0/3≤3 · 15sMP4/MOV · ≤3 · 15s total
AudioAdd reference audio0/3≤3MP3/WAV · ≤3 · needs image/video
Prompt
Upload up to 9 images, 3 videos, and 3 audio clips (12 references total). Use @Image, @Video, or @Audio in your prompt to identify each reference.
Inspiration
MiniMax H316:95s2K
MiniMax H316:95s2KGenerate MiniMax H3 Text-to-Video · Free
Prompt anatomy
Build a prompt that directs the shot
Give each phrase a job. The example below moves from subject and action to camera, light, pacing, and sound.
Prompt formula
Subject + action + setting + camera + lighting + pacing + sound
Example prompt
A lone cyclist crosses a rain-darkened bridge at blue hour. Slow side-tracking camera, wet reflections, restrained pace, soft tire spray, distant city ambience, cinematic natural light.
- 01
Choose Text to Video
Open the generator and keep MiniMax H3 selected. The text workflow is preselected on this page.
- 02
Write one clear shot
Name the subject and action first, then add setting, camera movement, lighting, pacing, and sound.
- 03
Select output settings
Choose an available aspect ratio, duration, and resolution for the destination where the clip will be used.
- 04
Generate and revise
Review motion and framing. Change one important instruction at a time so you can identify what improved the result.
Start without source media
When MiniMax H3 text to video is the best starting point
Text-to-video is the right starting mode when the scene exists as an idea rather than an asset. MiniMax H3 interprets the prompt as a shot plan, so concrete visual instructions usually outperform abstract adjectives. Use it for concept exploration first; move to image or reference mode when an exact composition or recognizable subject matters more than variation.
Describe camera behavior physically
Use directions such as slow dolly in, locked tripod, overhead drift, or side tracking instead of only saying cinematic.
Avoid competing scene changes
A short clip has limited time. One readable action and one camera idea usually produce a more coherent result than several cuts.
One-time MiniMax H3 credits
MiniMax H3 text-to-video pricing and credit packs
Choose a one-time credit pack for MiniMax H3 text-to-video generation. Every paid pack supports the same 2K prompt-to-video workflow without a recurring subscription.
Clear answers
MiniMax H3 text-to-video questions, answered
What is MiniMax H3 text to video?
It is a workflow that creates a video from a written scene description without requiring an uploaded source image.
How should I write a MiniMax H3 text-to-video prompt?
Describe the subject, action, setting, camera movement, lighting, pacing, and sound in that order. Keep the brief focused on one coherent shot.
Can MiniMax H3 turn text into video with sound?
MiniMax H3 prompts can describe both the picture and the audio direction. Include voice, ambience, music, or sound-effect cues when sound is part of the intended shot.
Can I make 2K text-to-video clips?
MiniMax H3 includes 2K output options. The generator displays the resolution, duration, and credit cost available for the selected setup before generation.
When should I use image-to-video instead?
Use image-to-video when you already have a composition, product still, illustration, or keyframe that should anchor the generated motion.