MiniMax H3 Multi-angle: H3 Max with the resident camera adapter.
The client provides a convenient way to interact with the model API.
npm install --save @fal-ai/clientSet FAL_KEY as an environment variable in your runtime.
export FAL_KEY="YOUR_API_KEY"The client API handles the API submit protocol. It will handle the request status updates and return the result when the request is completed.
import { fal } from "@fal-ai/client";
const result = await fal.subscribe("minimax/h3-max/camera-controls", {
input: {
prompt_expansion_mode: "disabled",
image_url: "https://storage.googleapis.com/falserverless/example_inputs/hailuo23/pro_i2v_in.jpg"
},
logs: true,
onQueueUpdate: (update) => {
if (update.status === "IN_PROGRESS") {
update.logs.map((log) => log.message).forEach(console.log);
}
},
});
console.log(result.data);
console.log(result.requestId);The API uses an API Key for authentication. It is recommended you set the FAL_KEY environment variable in your runtime when possible.
import { fal } from "@fal-ai/client";
fal.config({
credentials: "YOUR_FAL_KEY"
});The client API provides a convenient way to submit requests to the model.
import { fal } from "@fal-ai/client";
const { request_id } = await fal.queue.submit("minimax/h3-max/camera-controls", {
input: {
prompt_expansion_mode: "disabled",
image_url: "https://storage.googleapis.com/falserverless/example_inputs/hailuo23/pro_i2v_in.jpg"
},
webhookUrl: "https://optional.webhook.url/for/results",
});You can fetch the status of a request to check if it is completed or still in progress.
import { fal } from "@fal-ai/client";
const status = await fal.queue.status("minimax/h3-max/camera-controls", {
requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b",
logs: true,
});Once the request is completed, you can fetch the result. See the Output Schema for the expected result format.
import { fal } from "@fal-ai/client";
const result = await fal.queue.result("minimax/h3-max/camera-controls", {
requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b"
});
console.log(result.data);
console.log(result.requestId);Some attributes in the API accept file URLs as input. Whenever that's the case you can pass your own URL or a Base64 data URI.
You can pass a Base64 data URI as a file input. The API will handle the file decoding for you. Keep in mind that for large files, this alternative although convenient can impact the request performance.
You can also pass your own URLs as long as they are publicly accessible. Be aware that some hosts might block cross-site requests, rate-limit, or consider the request as a bot.
We provide a convenient file storage that allows you to upload files and use them in your requests. You can upload files using the client API and use the returned URL in your requests.
import { fal } from "@fal-ai/client";
const file = new File(["Hello, World!"], "hello.txt", { type: "text/plain" });
const url = await fal.storage.upload(file);Read more about file handling in our file upload guide.
prompt stringText prompt for video generation. When omitted or blank, defaults to preserving the frozen reference scene while only the camera moves. Default value: "The same elements in the reference are rigid. Preserve every element exactly. The entire scene is frozen. Only the camera moves. no scene motion only camera motion"
duration floatVideo length in seconds. The output can run up to about 0.7 s longer than requested. Default value: 5
resolution ResolutionEnumThe native generation resolution, or 1080P latent refinement from a native 768P source. Default value: "480P"
Possible enum values: 480P, 768P, 1080P
seed integerRandom seed. A random seed is selected when omitted.
enable_safety_checker booleanIf set to true, the safety checker will be enabled. Default value: true
sync_mode booleanReturn the generated video as base64 instead of a CDN URL.
prompt_expansion_mode string* requiredHow much effort to spend rewriting the prompt before generation. 'disabled' skips prompt expansion. 'balanced' returns in about a second. 'quality' spends up to ~30s on a richer prompt. Default value: "balanced"
image_url string* requiredURL of the image to use as the first frame.
Ordered camera keyframes. The first pose is held before its time and the final pose is held for the remainder of the video. Signed full turns are preserved, with at most 32 turns of total azimuth travel.
free_camera_preset EnumA fixed free-camera move. Truck, pedestal, and dolly slide the camera; pan, tilt, and roll turn it in place. The path is not editable. When this is set, camera_trajectory is ignored. Each move is one training-scale step: one near-depth unit, 30 degrees of pan, or 20 degrees of tilt or roll.
Possible enum values: truck_right, truck_left, pedestal_up, pedestal_down, dolly_in, dolly_out, pan_right, pan_left, tilt_up, tilt_down, roll_right, roll_left, s_curve_forward
Your own camera path, one pose per frame, e.g. sampled from a Blender camera. Poses span the whole clip evenly; only motion relative to the first pose is used. The first pose should be the camera that took image_url. When set, camera_trajectory and free_camera_preset are ignored.
camera_poses_scale floatMultiplier on imported camera translations. One model unit is the depth of the nearest scene content in the first frame, so a Blender scene whose nearest object is 5 m away needs 0.2. Default value: 1
{
"prompt": "Orbit precisely around the subject while preserving its identity and the scene.",
"duration": 5,
"resolution": "480P",
"enable_safety_checker": true,
"prompt_expansion_mode": "disabled",
"image_url": "https://storage.googleapis.com/falserverless/example_inputs/hailuo23/pro_i2v_in.jpg",
"camera_trajectory": [
{
"distance": 1,
"elevation": 0,
"time": 0,
"azimuth": 0
},
{
"distance": 0.2,
"elevation": 15,
"time": 0.3,
"azimuth": 45
},
{
"distance": 1,
"elevation": -90,
"time": 0.8,
"azimuth": 90
}
],
"camera_poses_scale": 1
}The generated video
expanded_prompt stringThe prompt after expansion, as sent to the model. Null when prompt expansion was disabled, left the prompt unchanged, or was performed internally by MiniMax's hosted API.
Timing breakdown in seconds. 'inference' is the DiT denoising time on the GPU backend. Null on routes that do not report backend timings.
{
"video": {
"url": "",
"content_type": "image/png",
"file_name": "z9RV14K95DvU.png",
"file_size": 4404019
}
}url string* requiredThe URL where the file can be downloaded from.
content_type stringThe mime type of the file.
file_name stringThe name of the file. It will be auto-generated if not provided.
file_size integerThe size of the file in bytes.
time float* requiredNormalized video time, from 0 at the start to 1 at the end.
azimuth float* requiredHorizontal camera angle around the subject, in degrees.
elevation float* requiredVertical camera angle around the subject, in degrees.
distance float* requiredCamera distance from the subject in normalized scene units.
convention ConventionEnum* requiredCamera axes of the matrices: blender (looks down -Z, Y up) or opencv (looks down +Z, Y down). The world frame does not matter.
Possible enum values: blender, opencv
One 4x4 row-major camera-to-world matrix per frame.