About MiniMax H3 Max: Text to Video
MiniMax H3 Max (Text to Video) is a post-trained variant of MiniMax H3, tuned by fal for stronger prompt adherence, better aesthetics, and higher throughput.
It generates 5 to 15 second clips at 480P or 768P resolution. Prompt expansion (balanced or quality) and multiple aspect ratios are supported.
See what this model can do
A handful of real prompts and their outputs.
Weather Timelapse
Supercell Over Wheat
"Timelapse cloud motion with layered storm structure and dramatic low sunlight."
Nature Spectacle
Lava Meets Ocean
"High-contrast night scene with glowing lava veins, surf and billowing steam."
Aviation
Dawn Marshalling
"Clear, readable hand signals and a large aircraft against a pink sunrise sky."
Action Sports
Sunset Kickflip
"Fast athletic motion with the board flipping under his feet in warm golden backlight."
Stop Motion
Origami Crane
"Handmade stop-motion look and a paper object that keeps its shape as it transforms and takes flight."
Anime
Seaside Bike Ride
"2D hand-painted anime style with cel shading, wind-blown hair and a cut to a smiling close-up."
Action Sports
Powder Tree Run
"Fast tracking action with big plumes of backlit powder spray."
Underwater
Jellyfish Drift
"Translucent, softly lit subjects with slow, hypnotic motion."
2D Animation
Mountain Dragon
"Traditional cel-animation look with painted backgrounds and a dramatic close-up."
Ready to build with MiniMax H3 Max: Text to Video?
Try MiniMax H3 Max: Text to Video in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.
curl -sSf -X POST https://hub.oxen.ai/api/ai/videos/generate \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OXEN_API_KEY" \
-d '{
"model": "minimax-h3-max-text-to-video",
"prompt": "A cat sitting on a chair",
"resolution": "768P",
"duration": 5,
"aspect_ratio": "16:9",
"enable_safety_checker": true,
"prompt_expansion_mode": "balanced",
"sync_mode": false
}'Request parameters
Every field MiniMax H3 Max: Text to Video accepts in the request body. See the API reference for response formats.
POST
https://hub.oxen.ai/api/ai/videos/generate| Field | Type | Required | Default | Description |
|---|---|---|---|---|
prompt | string | Yes | — | Text prompt for video generation |
resolution | string | No | "768P" | 480P768P |
duration | integer | No | 5 | Range: 5 – 15 |
aspect_ratio | string | No | "16:9" | 21:916:94:31:13:49:16 |
enable_safety_checker | boolean | No | true | If set to true, the safety checker will be enabled. |
prompt_expansion_mode | string | No | "balanced" | How much effort to spend rewriting the prompt before generation. 'balanced' returns in about a second. 'quality' spends up to ~30s on a richer prompt.balancedquality |
sync_mode | boolean | No | false | Return the generated video as base64 instead of a CDN URL. |
seed | integernullable | No | — | Random seed. A random seed is selected when omitted. |