Runway

Runway Gen 4.5

runway-gen-4.5/image-to-video

Upon release, it ranked first on the Artificial Analysis text-to-video leaderboard with 1247 Elo, showing outstanding prompt adherence, physics, and human motion, making it well suited for film storyboarding and brand short films

runway-gen-4.5/image-to-video runway-gen-4.5/text-to-video

Try runway-gen-4.5/image-to-video

Input

Showcases

View all showcases

Output

video

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

Pricing

runway-gen-4.5/image-to-video per second

Unit Price	$0.1715

Positioning Overview

Runway Gen-4.5 image-to-video pipeline: starting from a single first-frame image, combined with motion and camera descriptions, it generates a 5-, 8-, or 10-second video. It continues the series' strengths in prompt adherence and motion quality, making it suitable for film previsualization, advertising, and design exploration scenarios that need to extend a key art image, concept image, or product image into dynamic shots; accessed via the unified HiAPI.ai interface and billed by output seconds.

Core Highlights

Anchor the frame with a first-frame image — a single image serves as the first-frame input, and the output frame extends from that image, reducing the compositional drift that comes with text-only generation.
Adjustable duration and aspect ratio to delivery requirements — supports three duration tiers of 5, 8, and 10 seconds and five aspect ratios; the first-frame image is center-cropped to the selected ratio.
Prompts describe motion rather than redraw the frame — prompts focus on action and camera position descriptions, while the main subject is determined by the first-frame image, giving instructions and image a clear division of labor.

Capability Description

First-frame-driven video generation: upload a jpeg, png, or webp image as the first frame (up to 10MB), and the model generates a dynamic video from it, suitable for production stages where the composition is already fixed and motion needs to be added.

Motion and camera instruction control: prompts are used to describe actions and camera movement, with a maximum length of 1000 characters, making it easy to write camera positions and blocking intent from the storyboard directly into the generation parameters.

Parameterized duration and aspect ratio: choose durations of 5, 8, or 10 seconds, and aspect ratios of 16:9, 9:16, 4:3, 3:4, and 1:1 according to delivery needs, covering landscape, portrait, and square placement requirements.

Applicable Scenarios

Film and advertising storyboard artists: generate previs shots from keyframe images — use storyboard keyframes as the first frame to generate multi-second previs clips with camera movement, for internal review and shot-rhythm confirmation.
Brand and e-commerce design: turn product images into dynamic displays — use product key art as the first frame to generate short videos for vertical or square placements such as detail pages and feed advertising.
Concept design teams: explore the dynamic performance of static drafts — extend concept images into short dynamic clips to quickly compare different motion options before deciding the direction to take into formal production.

Limitations and Selection Advice

As an image-to-video pipeline, the main subject is determined by the first-frame image; prompts only control motion and camera and cannot change the composition or content of the first frame. The first frame supports only a single image and does not include SVG. Causal order and cross-frame object consistency in video generation may still deviate under complex shots; for shots that involve major compositional changes or long-sequence narrative, it is recommended to split the processing and budget for regeneration costs, or switch to a more suitable generation method.

Frequently asked questions

View all FAQs →

What first-frame image can I use?

One image per request in jpeg, png or webp, up to 10MB; SVG isn't supported. Ideally match the image to the output ratio. When they differ, the first frame is center-cropped, so keep the subject in the middle.
Can I add a last frame?

No. This model uses a single first frame, and the ending comes from the prompt and the model. To pin down the final picture, Kling 2.5 Turbo Image-to-Video accepts an optional last frame.
Which ratios, lengths and resolution are supported?

16:9, 9:16, 4:3, 3:4, 1:1, defaulting to 16:9; 5, 8 or 10 seconds in every ratio, defaulting to 5; resolution is fixed at 720p.
Is there audio in the output?

No. Clips are picture only, so add music and voice-over in your edit.

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: runway-gen-4.5/image-to-video

routestringOptional

Current fixed value: default

inputobjectRequired

Business parameters for runway-gen-4.5/image-to-video and route default — see the parameter table below.

promptstringRequiredminLength 1maxLength 1000

Text prompt describing the motion in the scene and camera movement, provided as a string, maximum 1000 characters.

durationintegerOptionalDefault: 5min 5max 10

Duration of the generated video as an integer in seconds, default 5.

Options:5810

image_urlsarrayRequiredminItems 1maxItems 1

Array of first-frame images; the array contains a single element, which is an image URL. Supports jpeg/png/webp formats, maximum 10MB per image, SVG is not supported.

Array [ string ]

aspect_ratiostringOptionalDefault: "16:9"

Aspect ratio of the output video as a string, default 16:9; the first-frame image will be center-cropped to this ratio.

Options:16:99:164:33:41:1

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": "runway-gen-4.5/image-to-video",
  "input": {
    "prompt": "…",
    "duration": 5,
    "image_urls": "…",
    "aspect_ratio": "16:9"
  }
}'

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: "runway-gen-4.5/image-to-video",
    input: {
      "prompt": "…",
      "duration": 5,
      "image_urls": "…",
      "aspect_ratio": "16:9"
    }
  }),
});
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": "runway-gen-4.5/image-to-video",
        "input": {
          "prompt": "…",
          "duration": 5,
          "image_urls": "…",
          "aspect_ratio": "16:9"
        }
    },
)
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"
    }
  }
}