Reference to video
Reference to Video AI
Give the model pictures, clips and audio to follow — a character, a style, a camera move, a voice — and say in the prompt how each one is used.
- Up to 12 files
- 9 images · 3 clips · 3 audio
- Type @ to name them
- Sound included
- Up to 15 s
Reference-to-video examples
Real renders from this site, with the exact prompt. Use one as a starting point.
“A street dancer spins on a rooftop at dusk, the camera circles her, city lights flicker on below, a punchy hip-hop beat”
Text · MiniMax H3 · 2K · 5s
Use this prompt“A golden retriever in a tiny yellow raincoat splashes through puddles on a city street, slow motion, water droplets sparkle, cheerful ukulele music”
Text · MiniMax H3 Max · 1080P · 6s
Use this prompt“Macro shot of coffee being poured into a glass cup of iced milk, swirling clouds of cream, warm morning light, soft café ambience”
Text · MiniMax H3 · 768P · 5s
Use this prompt“A tiny orange kitten chases a soap bubble across a sunlit wooden floor, slow motion, playful piano music”
Text · MiniMax H3 Max · 480P · 5s
Use this prompt“The paper boat starts to spin slowly as the rain gets heavier, the camera pulls back to reveal the whole street”
Image · MiniMax H3 Max · 480P · 5s
Use this prompt“In the style and mood of the reference video, a yellow paper boat sails across a puddle in a sunny park, children laughing”
Reference · MiniMax H3 Max · 480P · 5s
Use this prompt
Guide the video with references
References are files the model follows without using them as frames: a character's face and outfit, the look of a scene, the rhythm of a camera move, the voice or music you want.
Each upload gets a name in order — Image 1, Image 2, Video 1, Audio 1 — the way MiniMax H3 prompts refer to them. Type @ in the prompt to insert one, then say what it's for: "Image 1 is the main character, follow the camera move in Video 1".
Clips must be 2–15 seconds and 15 seconds in total per kind; reference video is billed per second like output, and the first reference images are included in the price.
MiniMax H3 AI is an independent service and is not affiliated with or endorsed by MiniMax. MiniMax, Hailuo and MiniMax H3 are trademarks of their owners.
How it works
Three steps, a couple of minutes, no GPU.
- 01
Describe the shot
Say what happens: subject, action, camera, light and sound. Or start from an example.
- 02
Add pictures or references
Optional: a first or last frame, or reference images, clips and audio to follow.
- 03
Generate and download
Pick the model, resolution and length, see the price, and download the MP4 when it's ready.
More ways to create
MiniMax H3
The flagship: native 2K, up to 15 s, sound included.
Hailuo AI (Hailuo 3)
MiniMax's Hailuo 3 model, online with no app.
MiniMax H3 Max
Faster and cheaper, 480P to 1080P — for drafts.
Text to video
Describe a shot and get a video with sound.
Image to video
Animate a picture, or move from one image to another.
Reference to video questions
Choose Reference above, add images, clips or audio, then describe the new video and what each reference is for. The model keeps what you point it to and generates the rest.
By upload order: Image 1, Image 2, Video 1, Audio 1. Type @ in the prompt box to pick one, or use the chips under the box.
Up to 9 images, 3 clips and 3 audio files, 12 files in total. Clips are 2–15 seconds each and 15 seconds in total; audio needs at least one image or clip.
Reference video is billed per second like the output. The first reference images are included (2 on H3 Max, 5 on H3); extra ones cost a few credits each. The button shows the total.
Image to video uses your picture as the actual first (and last) frame. Reference mode uses pictures and clips as guides, so the video can show the character or style in a brand-new shot.
They're used only to make your video and deleted 30 days later. Use files you own or have permission to use.
Make your first MiniMax H3 video
Write a sentence, pick a length, and hear it come to life.
Start creating