minimax/h3-max/image-to-video

fal's H3 Max is a post-trained variant of MiniMax H3, tuned for stronger prompt adherence and better aesthetics while co-optimized with our custom inference stack for higher throughput with no compromises on output quality

Learn more about H3

Inference

Commercial use

Schema AsyncAPI

LLMs

Playground API Examples

Open in Sandbox

1. Calling the API

2. Authentication

API Key

3. Queue

4. Files

5. Schema

About

Image-text-to-video: image_url optional; text-only routes to t2v.

1. Calling the API#

Install the client#

The client provides a convenient way to interact with the model API.

npm install --save @fal-ai/client

Migrate to @fal-ai/client

The @fal-ai/serverless-client package has been deprecated in favor of @fal-ai/client. Install the new package and update your imports — see client setup.

Setup your API Key#

Set FAL_KEY as an environment variable in your runtime.

export FAL_KEY="YOUR_API_KEY"

Submit a request#

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/image-to-video", {
  input: {
    prompt: "The camera slowly pulls back from the scene, revealing the full landscape as clouds drift overhead and light shifts across the terrain.",
    prompt_expansion_mode: "disabled"
  },
  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);

2. Authentication#

The API uses an API Key for authentication. It is recommended you set the FAL_KEY environment variable in your runtime when possible.

API Key#

In an environment where you cannot set environment variables, you can configure the API key manually on the client.

import { fal } from "@fal-ai/client";

fal.config({
  credentials: "YOUR_FAL_KEY"
});

Protect your API Key

When running code on the client-side (e.g. in a browser, mobile app or GUI applications), make sure to not expose your FAL_KEY. Instead, use a server-side proxy to make requests to the API. For more information, check out our server-side integration guide.

3. Queue#

Long-running requests

For long-running requests, such as training jobs or models with slower inference times, it is recommended to check the Queue status and rely on Webhooks instead of blocking while waiting for the result.

Submit a request#

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/image-to-video", {
  input: {
    prompt: "The camera slowly pulls back from the scene, revealing the full landscape as clouds drift overhead and light shifts across the terrain.",
    prompt_expansion_mode: "disabled"
  },
  webhookUrl: "https://optional.webhook.url/for/results",
});

Fetch request status#

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/image-to-video", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b",
  logs: true,
});

Get the result#

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/image-to-video", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b"
});
console.log(result.data);
console.log(result.requestId);

4. Files#

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.

Data URI (base64)#

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.

Hosted files (URL)#

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.

Uploading files#

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);

Auto uploads

The client will auto-upload the file for you if you pass a binary object (e.g. File, Data).

Read more about file handling in our file upload guide.

5. Schema#

Input#

prompt string* required

Text prompt for video generation

duration integer

The duration of the video in seconds. Default value: 5

resolution ResolutionEnum

The native generation resolution, or 1080P latent refinement from a native 768P source. Default value: "768P"

Possible enum values: 480P, 768P, 1080P

seed integer

Random seed. A random seed is selected when omitted.

enable_safety_checker boolean

If set to true, the safety checker will be enabled. Default value: true

sync_mode boolean

Return the generated video as base64 instead of a CDN URL.

prompt_expansion_mode string* required

How 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

Optional URL of the image to use as the first frame. When provided, the output canvas follows this image. If only end_image_url is provided, the canvas follows that last frame instead. If both images are omitted, the request is handled as text-to-video (16:9 by default).

end_image_url string

Optional URL of the image to use as the last frame. It may be provided alone for end-only keyframe generation; in that case the output canvas follows this image.

{
  "prompt": "The camera slowly pulls back from the scene, revealing the full landscape as clouds drift overhead and light shifts across the terrain.",
  "duration": 5,
  "resolution": "768P",
  "enable_safety_checker": true,
  "prompt_expansion_mode": "disabled",
  "image_url": "https://storage.googleapis.com/falserverless/example_inputs/hailuo23/pro_i2v_in.jpg"
}

Output#

video File* required

The generated video

expanded_prompt string

The 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.

timings object

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
  }
}

Other types#

File#

url string* required

The URL where the file can be downloaded from.

content_type string

The mime type of the file.

file_name string

The name of the file. It will be auto-generated if not provided.

file_size integer

The size of the file in bytes.

TranscriptSegment#

start float* required

Speech start in source-video seconds.

end float* required

Speech end in source-video seconds.

text string* required

Source text, or final dialogue when auto_translate is false.

DubbingSegment#

start float* required

end float* required

text string* required

translated_text string* required

H3MaxCameraKeyframe#

time float* required

Normalized video time, from 0 at the start to 1 at the end.

azimuth float* required

Horizontal camera angle around the subject, in degrees.

elevation float* required

Vertical camera angle around the subject, in degrees.

distance float* required

Camera distance from the subject in normalized scene units.

CheckpointLoRA#

locator string* required

Opaque service-owned adapter locator.

sha256 string* required

size_bytes integer* required

scale float* required

transformer_family TransformerFamilyEnum* required

Possible enum values: fl2va, ref2va, ref2va-tdm-k10

transformer_variant string* required

AVCheckpoint#

url string* required

Unguesseable service-issued checkpoint artifact URL.

sha256 string* required

size_bytes integer* required

version integer

Default value: 1

model string

Default value: "minimax-h3"

transformer_family TransformerFamilyEnum

Default value: "fl2va"

Possible enum values: fl2va, ref2va, ref2va-tdm-k10

loras list<CheckpointLoRA>

resolution ResolutionEnum* required

Possible enum values: 480p, 544p, 640p, 704p, 768p, 1080p, 1440p

checkpoint_id string* required

owner_id string* required

sha256 of the issuing caller's gateway identity.

source_request_id string* required

Issuing request id — audit/provenance lineage only.

issued_at integer* required

expires_at integer* required

audience string

Default value: "minimax-h3/continue-video"

signature string* required

Service HMAC binding the complete descriptor.

StartSessionRequest#

sdp string* required

type string

Default value: "offer"

session_id string

ice_servers list<object>

ice_status string

credential_age_seconds float

DirectorInfo#

app string

Default value: "minimax-h3-max-director"

protocol_version integer

Default value: 1

default_chunk_duration integer

Default value: 10

chunk_seconds integer

Default value: 10

min_chunk_duration integer

Default value: 5

max_chunk_duration integer

Default value: 15

continuation_context_frames integer

Default value: 39

continuation_playback_seconds float

Default value: 8.5

fps integer

Default value: 24

audio_sample_rate integer

Default value: 48000

conditioning_audio_sample_rate integer

Default value: 32000

audio_bitrates list<Enum>

default_audio_bitrate Enum

Possible enum values: 96000, 128000, 192000

aspect_ratios list<Enum>

resolutions list<Enum>

max_session_seconds float

session_limit_scope SessionLimitScopeEnum

Default value: "configured"

Possible enum values: configured, effective

prompt_expander string

Default value: "fast"

one_session_per_machine boolean

Default value: true

controller_machine_type string

Default value: "XL"

backend_selection string

Default value: "minimax-h3-turbo-balancer"

prompt_deck_size integer

Default value: 6

audio_conditioning boolean

Default value: true

audio_behaviors list<Enum>

max_audio_source_seconds float

Default value: 600

prompt_context_segments integer

Default value: 12

default_memory integer

Default value: 12

min_memory integer

Default value: 1

max_memory integer

Default value: 50

default_acceleration string

Default value: "regular"

accelerations list<Enum>

scripts boolean

Default value: true

script_modes list<Enum>

script_max_beats integer

Default value: 64

script_max_end_images integer

Default value: 16

script_max_audio_beats integer

Default value: 8

script_max_queued integer

Default value: 4

script_max_pending integer

Default value: 4

script_max_decoded_audio_bytes integer

Default value: 67108864

script_session_max_decoded_audio_bytes integer

Default value: 335544320

script_min_end_image_spacing_seconds integer

Default value: 3

script_min_chunk_seconds integer

Default value: 3

script_min_opening_chunk_seconds integer

Default value: 5

client_message_types list<Enum>

server_message_types list<Enum>

minimax/h3-max/image-to-video

Table of contents

1. Calling the API

2. Authentication

3. Queue

4. Files

5. Schema

About

1. Calling the API#

Install the client#

Migrate to @fal-ai/client

Setup your API Key#

Submit a request#

2. Authentication#

API Key#

Protect your API Key

3. Queue#

Long-running requests

Submit a request#

Fetch request status#

Get the result#

4. Files#

Data URI (base64)#

Hosted files (URL)#

Uploading files#

Auto uploads

5. Schema#

Input#

Output#

Other types#

File#

TranscriptSegment#

DubbingSegment#

H3MaxCameraKeyframe#

CheckpointLoRA#

AVCheckpoint#

StartSessionRequest#

DirectorInfo#

Related Models