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.
- A Product in Psychedelic Hand-Drawn Motion
The original creator published the complete generation prompt for a product in psychedelic hand-drawn motion on X. Native-video output: 15s · 2560×1440. The creator published the c
MiniMax H3 · text-to-video · 0 recorded input roles
- Bureaucracy Explained in Fifteen Seconds
The original creator published the complete generation prompt for bureaucracy explained in fifteen seconds on X. Native-video output: 15s · 1536×2688. The creator published the com
MiniMax H3 · text-to-video · 0 recorded input roles
- Five Loaves and Two Fish in Stained Glass
The original creator published the complete generation prompt for five loaves and two fish in stained glass on X. Native-video output: 15s · 1956×1088. The creator published the co
MiniMax H3 · text-to-video · 0 recorded input roles
- Pangu Splits the World in Lacquer and Mother-of-Pearl
The original creator published the complete generation prompt for pangu splits the world in lacquer and mother-of-pearl on X. Native-video output: 15s · 1280×736. The creator publi
MiniMax H3 · text-to-video · 0 recorded input roles
- An After-Hours Experiment in an Art Gallery
The original creator published the complete generation prompt for an after-hours experiment in an art gallery on X. Native-video output: 8s · 1280×736. The creator published the co
MiniMax H3 · text-to-video · 0 recorded input roles
- A Playful Performance Close to Camera
The original creator published the complete generation prompt for a playful performance close to camera on X. Native-video output: 10s · 842×474. The creator published the complete
MiniMax H3 · reference-to-video · 0 recorded input roles
- A Song Lip-Sync Across Two Models
The original creator published the complete generation prompt for a song lip-sync across two models on X. Native-video output: 15s · 1440×2560. The creator published the complete p
MiniMax H3 · reference-to-video · 0 recorded input roles
- Images and Typography in Seamless Motion
The original creator published the complete generation prompt for images and typography in seamless motion on X. Native-video output: 15s · 2944×1248. The creator published the com
MiniMax H3 · reference-to-video · 1 recorded input roles
- A Fearless Warrior Battles a Giant Monster
The original creator published the complete generation prompt for a fearless warrior battles a giant monster on X. Native-video output: 15s · 2560×1440. The creator published the c
MiniMax H3 · text-to-video · 0 recorded input roles
- Drowning Deep Down the Ocean
The original creator published the complete generation prompt for drowning deep down the ocean on X. Native-video output: 15s · 1920×1080. The creator published the complete prompt
MiniMax H3 · text-to-video · 0 recorded input roles
- A Taste of Bangkok Street Food
The original creator published the complete generation prompt for a taste of bangkok street food on X. Native-video output: 15s · 2560×1440. The creator published the complete prom
MiniMax H3 · text-to-video · 0 recorded input roles
- A Fearless Traveler Enters a Forgotten Kingdom
The original creator published the complete generation prompt for a fearless traveler enters a forgotten kingdom on X. Native-video output: 15s · 2560×1440. The creator published t
MiniMax H3 · text-to-video · 0 recorded input roles