MiniMax H3 source prompts: choose the right input mode
628 source examples; not independently reproduced and no identical-result promise.
How to choose an example
This collection contains the main H3 model, not Fast or Max. Its current Studio settings are 4–15 seconds and 768P/2K.
Choose text, frame or reference from your actual inputs; frame roles and reference roles belong to separate tasks.
Check each model, input role and known setting. Attribution is not a media reuse grant; supply your own inputs.
- Add A Teammate In Uniform
Add a person in matching team uniform on the left, mirroring the action of others.
MiniMax H3 · reference-to-video · 1 recorded input roles
- Swap Child For Dog And Change Jacket
Replace the child at the back with a golden retriever and change the leftmost child's jacket to denim.
MiniMax H3 · reference-to-video · 3 recorded input roles
- High-Precision Instruction Following
Replace objects, modify furniture, remove effects, and add elements based on a reference video.
MiniMax H3 · reference-to-video · 1 recorded input roles
- High-Precision Instruction Following
Replace products, modify signage, and change final dialogue based on a reference video.
MiniMax H3 · reference-to-video · 1 recorded input roles
- Precise Instruction Following
Two stage magicians swap black and white suit colors while their gloves stay unchanged, then bow as the red curtain closes and turns deep blue.
MiniMax H3 · reference-to-video · 1 recorded input roles
- Precise Instruction Following
Add orange hand-drawn sparks around two people in a reference video, building to bright light as they approach and pink brushstrokes when they kiss.
MiniMax H3 · reference-to-video · 2 recorded input roles
- Style Presets
A ten-second trap music video pairs two detective rappers with gritty print textures, bold animated typography, and close-up cuts synchronized to the beat.
MiniMax H3 · reference-to-video · 3 recorded input roles
- Three-reference singing performance
Combine a camera-motion video, a character image and a vocal reference in one singing performance.
MiniMax H3 · reference-to-video · 3 recorded input roles
- After the Fleet Jumps
Moves from a medium-wide view of a starship bridge to a close-up of the captain, using native stereo audio to synchronize the fleet jump, spatial shock, and the suddenly quiet afte
MiniMax H3 · text-to-video · 0 recorded input roles
- Ramen Rack Focus
Uses a ramen image as the opening-frame constraint, then gradually racks focus so the foreground steam softens while the family in the background comes into view, testing depth of
MiniMax H3 · image-to-video · 1 recorded input roles
- Follow the Wind
References a source video, its original background music, and an additional voice timbre to add English dialogue while preserving character identity, wardrobe, framing, and setting
MiniMax H3 · reference-to-video · 3 recorded input roles
- The Diner That Rewinds
Inside a 1950s diner, coffee, dishes, and food freeze in mid-air after a collision. The camera circles the scene before the entire world rewinds to its starting state. The original
MiniMax H3 · text-to-video · 0 recorded input roles