About MiniMax H3 Max: Reference to Video
MiniMax H3 Max (Reference to Video) is a post-trained variant of MiniMax H3, tuned by fal for stronger prompt adherence and better aesthetics. It generates video from a text prompt guided by multimodal references: up to 9 subject or style images, 3 motion video clips, and 3 audio clips.
It generates 5 to 15 second clips at 480P or 768P resolution with audio, including lip-synced dialogue, keeping subjects consistent with their reference images while following referenced motion and voices. References may total at most 12 files; video and audio clips run 2 to 15 seconds each with at most 15 seconds combined per type, and audio cannot be the only reference. Prompt expansion modes trade latency for prompt fidelity.
See what this model can do
A handful of real prompts and their outputs.
Ready to build with MiniMax H3 Max: Reference to Video?
Try MiniMax H3 Max: Reference 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-reference-to-video",
"prompt": "A cat sitting on a chair",
"aspect_ratio": "adaptive",
"resolution": "768P",
"duration": 5,
"prompt_expansion_mode": "balanced",
"enable_safety_checker": true,
"sync_mode": false
}'Request parameters
Every field MiniMax H3 Max: Reference to Video accepts in the request body. See the API reference for response formats.
https://hub.oxen.ai/api/ai/videos/generate| Field | Type | Required | Default | Description |
|---|---|---|---|---|
prompt | string | Yes | — | Text prompt for video generation. Use @Image1, @Image2, ... to reference the reference images in order, @Video1, ... for the reference videos, and @Audio1, ... for the reference audio; each type is numbered separately. |
input_images | array<string>nullable | No | — | Reference images for subjects or style, up to 9. Order maps to @Image1, @Image2, etc. in the prompt. Reference images, videos, and audio must total at most 12 files. |
input_videos | array<string>nullable | No | — | Reference video clips for motion or style, up to 3 clips of 2 to 15 seconds (15 seconds combined). Order maps to @Video1, @Video2, etc. in the prompt. Reference images, videos, and audio must total at most 12 files. |
input_audios | array<string>nullable | No | — | Reference audio for voices or sound, up to 3 clips of 2 to 15 seconds (15 seconds combined). Order maps to @Audio1, @Audio2, etc. in the prompt. Cannot be the only reference input; provide at least one reference image or video with it. |
aspect_ratio | string | No | "adaptive" | The aspect ratio of the generated video.adaptive21:916:94:31:13:49:16 |
resolution | string | No | "768P" | The native generation resolution of the video.480P768P |
duration | integer | No | 5 | The duration of the video in seconds. Range: 5 – 15 |
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 |
enable_safety_checker | boolean | No | true | If set to true, the safety checker will be enabled. |
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. |