Lightricks

LTX 2.5 Fast

ltx-2.5-fast/image-to-video

Lightricks' accelerated video generation model supports text-to-video and image-to-video, generating visuals and audio in sync, ideal for rapid output and prototype validation

ltx-2.5-fast/image-to-video ltx-2.5-fast/text-to-video

Try ltx-2.5-fast/image-to-video

Input

Showcases

View all showcases

Output

video

Fill in the parameters and run — results show up here.

Pricing

ltx-2.5-fast/image-to-video per second

Specifications	Unit Price
1080P	$0.086

Overview

ltx-2.5-fast/image-to-video is a fast image-to-video model from Lightricks that generates video clips with synchronized audio starting from a still image. It supports first-frame/last-frame interpolation and can be combined as needed across 2–20 second durations, 720p or 1080p resolutions, and landscape or portrait orientations, making it suitable for developers who need to quickly validate shot direction or produce short video assets in batches.

Key Highlights

First-frame/last-frame interpolation controls shot transitions — you can pass in a first-frame image and then add a last-frame image, letting the model generate a smooth transition between the two points to lock down the starting and ending compositions.
Video and native audio generated in sync — by default, native audio is produced together with the visuals, reducing the post-production work of aligning audio and video.
Flexible combinations of duration and aspect ratio — supports 2–20 seconds, 720p or 1080p, and landscape or portrait, so you can quickly switch output specs by distribution channel.

Capabilities

Image-to-video and first-frame/last-frame interpolation: Generates dynamic video based on a single first-frame image; after adding a second image as the last frame, the model interpolates a transition between the start and end, making it suitable for shots that require precise control over the opening and closing frames.

Parametrized duration and aspect ratio: Duration can be selected in even-second increments from 2 to 20 seconds, resolution supports 720p and 1080p, and aspect ratio supports 16:9 and 9:16, so a single call can output landscape or portrait assets for the target platform.

Synchronized audio-video generation: The generate_audio parameter controls whether native audio is produced in sync when generating video; it is enabled by default and is suitable for scenarios that need a finished clip with sound directly.

Prompts describe scenes and camera movement: The prompt field accepts up to 5000 characters and can describe the scene, motion, camera, and sound at the same time, making the generated result closer to the creator's intended shot.

Use Cases

Developers doing rapid prototype validation — use a concept image plus a short prompt to quickly generate a short clip, testing shot direction and style at low cost before deciding whether to move into refined production.
Batch asset production for social media and advertising — generate 2–20 second clips with audio in 9:16 portrait and 16:9 landscape respectively, for short-video distribution or as batch options for ad assets.
Producing first-frame/last-frame transition shots — provide two images, a first frame and a last frame, to generate the in-between transition animation, for use in transitions, product showcases, or storyboard shots that need locked start and end compositions.

Limitations and Selection Advice

This model is positioned as a speed-optimized version; when the duration exceeds 10 seconds, it only supports 720p or 1080p, and the frame rate is limited to 24/25 FPS. Extra-long durations and high resolution cannot be satisfied at the same time, so you need to trade off between duration and resolution according to the scenario. If you need output with longer duration or higher frame rate, you should evaluate other versions in the same series. The input must include at least one first-frame image; for text-only video generation scenarios, use the text-to-video pipeline.

Frequently asked questions

View all FAQs →

Which resolutions does LTX 2.5 Fast support?

720p and 1080p, with 720p as the default, for both text-to-video and image-to-video.
How long can a clip be?

2 to 20 seconds: 2, 3, 4, 5, 6, 8, 10, 12, 14, 16, 18 or 20, with 6 as the default.
Does it support vertical video?

Yes. Set aspect_ratio to 9:16 for vertical output; the default is 16:9 landscape.
What is native audio, and does it cost extra?

With generate_audio on (the default) the model also creates ambience, effects or music. Turning it off gives a silent clip at the same price.

Create a generation task

POST https://api.hiapi.ai/v1/tasks

Headers

AuthorizationstringRequired

Account API key. Required on every request. Example: Bearer YOUR_HIAPI_API_KEY. Get your API key

Content-TypestringOptional

The request body is always parsed as JSON; when sent, only application/json (optionally with charset) is accepted — any other value returns 415. Example: application/json.

Idempotency-KeystringOptional

Idempotency key, up to 255 bytes. Retries with the same key from the same account create the task only once; replays return the original taskId.

Idempotency key

On network timeouts or client retries, the same key creates the task only once — no double charges (scope: the API key's account). Use a business-unique identifier as the key (e.g. "order-42"); replays return the original taskId, and keys expire 24 hours after the first request. See the Unified Async API overview for the full scenario matrix.

Body

modelstringRequired

Current fixed value: ltx-2.5-fast/image-to-video

routestringOptional

Current fixed value: default

inputobjectRequired

Business parameters for ltx-2.5-fast/image-to-video and route default — see the parameter table below.

promptstringRequiredminLength 1maxLength 5000

Text prompt describing the scene, motion, camera, and audio of the video. Value is a string.

durationintegerOptionalDefault: 6min 2max 20

Video duration in seconds. Value is an integer, default 6.

Options:2345681012

Show all (4)

14161820

image_urlsarrayRequiredminItems 1maxItems 2

Array of first-frame and last-frame image URLs: the first URL is the first frame, and when a second URL is appended it is used as the last frame. Supports jpeg, png, and webp formats.

Array [ string ]

resolutionstringOptionalDefault: "720p"

Resolution of the output video. Takes a string, default 720p.

Options:720p1080p

aspect_ratiostringOptionalDefault: "16:9"

Aspect ratio of the output image, used to select landscape or portrait output. Takes a string, default 16:9.

Options:16:99:16

generate_audiobooleanOptionalDefault: true

Whether to generate native audio while generating the video. Takes a boolean value, default true.

callbackobjectOptional

Terminal-state notification config. When omitted, no callback is delivered — poll the task yourself. See the callback note below.

Callbacks (Webhook)

Provide callback.url when creating a task and HiAPI POSTs to your service once the task reaches a terminal state — no polling needed. The callback payload mirrors the task detail structure; signature verification, delivery retries and idempotency are documented on the Unified Async API overview page.

urlstringRequired

Required when callback is present. A POST is sent to this URL once the task reaches a terminal state; must be a valid http(s) URL.

whenstringOptionalDefault: "final"

Only final is supported today — notified on both success and fail.

Options:final

storagestringOptionalDefault: "temp"

Artifact storage tier: temp (default, retained about 7 days) or persistent (long-term, billed by size). Insufficient balance or exceeding the storage cap silently downgrades to temp; the effective tier is shown in the task detail response.

Options:temppersistent

Request examples

# Submit an async task; returns a taskId immediately (no waiting for generation)
curl -X POST "https://api.hiapi.ai/v1/tasks" \
  -H "Authorization: Bearer $HIAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "ltx-2.5-fast/image-to-video",
  "input": {
    "prompt": "…",
    "duration": 6,
    "image_urls": "…",
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "generate_audio": true
  }
}'

const res = await fetch("https://api.hiapi.ai/v1/tasks", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.HIAPI_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "ltx-2.5-fast/image-to-video",
    input: {
      "prompt": "…",
      "duration": 6,
      "image_urls": "…",
      "resolution": "720p",
      "aspect_ratio": "16:9",
      "generate_audio": true
    }
  }),
});
const task = await res.json();
// { code: 200, message: "success", data: { taskId } }

import os, requests

res = requests.post(
    "https://api.hiapi.ai/v1/tasks",
    headers={"Authorization": f"Bearer {os.environ['HIAPI_API_KEY']}"},
    json={
        "model": "ltx-2.5-fast/image-to-video",
        "input": {
          "prompt": "…",
          "duration": 6,
          "image_urls": "…",
          "resolution": "720p",
          "aspect_ratio": "16:9",
          "generate_audio": True
        }
    },
)
print(res.json())  # { code, message, data: { taskId } }

200 OK

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-01HZTQ8BX2N3GM3YFK4Z9D7VQR"
  }
}

400 Bad Request

{
  "code": 400,
  "message": "invalid request",
  "data": null,
  "error_code": "INVALID_REQUEST"
}

Get task detail

GET https://api.hiapi.ai/v1/tasks/:id

Response fields

taskIdstringRequired

Task ID, always prefixed with tk-hiapi-.

modelstringRequired

Resolved full model name. Tasks submitted with the route parameter return base@route (e.g. gpt-image-2/text-to-image@ext); otherwise identical to the name passed at creation.

routestringOptional

Present only when the task was submitted with an explicit route parameter; echoes the submitted value.

statusstringRequired

Task status.

Status values

queued Queued, not started yet. handling Being processed. archiving Processing finished, artifacts being prepared. success Terminal: completed, artifacts available (output returned). fail Terminal: failed (error returned). After submission, check status: success and fail are terminal, everything else is non-terminal. Poll every 1–3 seconds until terminal. On success, download artifacts from output[].url and transfer them before expireAt; pass storage: "persistent" at creation time when long-term retention is needed.

creatednumberRequired

Task creation time (Unix seconds).

completednumberRequired

Unix seconds when the task reached a terminal state; fixed to 0 while not terminal.

outputarrayOptional

Present only when status == success. Artifact list — always an array; a single task may return multiple types at once (e.g. video + first_frame).

Array [ object ]

Array items

urlstringRequired

Artifact URL, directly downloadable.

typestringRequired

Current possible values: video, image, audio, first_frame, last_frame, thumbnail; more may be added later.

expireAtnumberRequired

Unix seconds until which the artifact remains accessible; download or transfer before it expires.

errorobjectOptional

Present only when status == fail.

codestringRequired

Business error code.

messagestringRequired

Error description.

Response examples

Success

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-01HZTQ8BX2N3GM3YFK4Z9D7VQR",
    "model": "happyhorse-1-0",
    "status": "success",
    "created": 1777282033,
    "completed": 1777282099,
    "output": [
      {
        "url": "https://cdn.hiapi.ai/tasks/.../video.mp4",
        "type": "video",
        "expireAt": 1777886899
      }
    ]
  }
}

Processing (non-terminal)

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-...",
    "model": "happyhorse-1-0",
    "status": "archiving",
    "created": 1777282033,
    "completed": 0
  }
}

Failed

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-...",
    "model": "happyhorse-1-0",
    "status": "fail",
    "created": 1777282033,
    "completed": 1777282099,
    "error": {
      "code": "TASK_FAILED",
      "message": "task failed"
    }
  }
}