Seedream 5.0 Pro 正式上线 | 在图像生成器中体验 →

Gen4 Aleph

runwayml /

RunwayML Gen4 Aleph is a Video-to-Video model for editing, transforming, and generating video at $0.18 per second. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

video-to-video
输入

就绪

$0.9每次运行·~11 / $10

下一步:

示例查看全部

Remove people from the video.

Replace the fox in the video with a rabbit.

Remove flying birds.

Change to anime style

Remove the swallows.

The blisters blown by the woman are turtles.

Changed to anime style.

The girl turned to face the screen.

Change the woman's clothes to red.

Swap robots for robot dogs.

相关模型

README

Runway Gen4 Aleph

Transform your videos with natural language instructions. Runway Gen4 Aleph is a powerful video-to-video model that understands text prompts to edit, modify, and reimagine your footage — from removing objects to changing environments and styles.

Why It Looks Great

  • Natural language editing: Simply describe what you want changed — remove objects, alter backgrounds, modify styles.
  • Context-aware transformations: Understands scene structure and maintains visual coherence throughout edits.
  • Reference image guidance: Optionally provide a reference image to guide the visual style or target appearance.
  • Flexible aspect ratios: Supports 16:9, 4:3, 1:1, 3:4, and 9:16 for any output format.
  • Prompt Enhancer: Built-in tool to help refine and improve your editing instructions.
  • Temporal consistency: Maintains smooth, stable results across all frames.

Parameters

ParameterRequiredDescription
promptYesText instruction describing the edit (e.g., "Remove people from the video").
videoYesSource video file (upload or public URL).
aspect_ratioNoOutput aspect ratio: 16:9, 4:3, 1:1, 3:4, or 9:16. Default: 16:9.
reference_imageNoReference image to guide style or appearance (upload or URL).

How to Use

  1. Write your prompt — describe the transformation you want (e.g., "Remove people from the video", "Change the sky to sunset", "Make it look like a watercolor painting").
  2. Use Prompt Enhancer (optional) — click the button to refine your instructions for better results.
  3. Upload your video — drag and drop or paste a public URL.
  4. Choose aspect ratio — select the output format that fits your needs.
  5. Add reference image (optional) — provide visual guidance for the target style.
  6. Run — click the button to start processing.
  7. Download — preview and save your transformed video.

Pricing

Per-second billing based on input video duration.

MetricCost
Per second$0.18

Examples

Video LengthCalculationTotal Cost
5s5 × $0.18$0.90
10s10 × $0.18$1.80
30s30 × $0.18$5.40

Best Use Cases

  • Object Removal — Remove unwanted people, objects, or distractions from footage.
  • Environment Changes — Transform backgrounds, skies, or settings without reshooting.
  • Style Transfer — Apply artistic styles, color grades, or visual aesthetics to existing videos.
  • Visual Effects — Add weather effects, lighting changes, or atmospheric modifications.
  • Content Repurposing — Adapt existing footage for new contexts or creative directions.

Example Prompts

  • "Remove people from the video"
  • "Change the background to a tropical beach"
  • "Make it look like a vintage film from the 1970s"
  • "Add snow falling throughout the scene"
  • "Transform into an anime style"
  • "Replace the sky with a dramatic sunset"

Pro Tips for Best Results

  • Be specific and clear in your prompts — describe exactly what you want changed and how.
  • Use the Prompt Enhancer to improve vague or simple instructions.
  • For style changes, provide a reference image that captures the target aesthetic.
  • Start with shorter clips to test your prompt before processing longer videos.
  • Combine object removal with style changes in a single prompt for complex edits.

Notes

  • If using URLs for video or reference image, ensure they are publicly accessible. A preview in the interface confirms successful loading.
  • Processing time scales with video duration and complexity of the requested edit.
  • Complex transformations may require more descriptive prompts for best results.
提示:本网站部分功能由第三方 AI 模型提供支持。

Gen4 Aleph API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/runwayml/gen4-aleph with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Gen4 Aleph below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
    "aspect_ratio": "16:9"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/runwayml/gen4-aleph" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d "$REQUEST_BODY")

TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
  RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
    -H "Authorization: Bearer $WAVESPEED_API_KEY")
  RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
  STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
  case "$STATUS" in
    completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
  esac
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/runwayml/gen4-aleph";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');

async function requestJson(url, options = {}) {
  const response = await fetch(url, options);
  if (!response.ok) throw new Error(await response.text());
  return response.json();
}

// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
        "aspect_ratio": "16:9"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;

// 2. Poll until the prediction finishes.
while (true) {
  const resultBody = await requestJson(resultUrl, {
    headers: { "Authorization": `Bearer ${apiKey}` },
  });
  const result = resultBody.data ?? resultBody;
  if (result.status === "completed") {
    console.log(result.outputs);
    break;
  }
  if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
  if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
  await new Promise(resolve => setTimeout(resolve, 2000));
}
Python example
import json
import os
import time
from urllib.request import Request, urlopen

api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
    "aspect_ratio": "16:9"
}

def request_json(url, data=None):
    request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
    with urlopen(request) as response:
        return json.load(response)

# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/runwayml/gen4-aleph", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
    raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"

# 2. Poll until the prediction finishes.
while True:
    result_body = request_json(result_url)
    result = result_body.get("data", result_body)
    status = result.get("status")
    if status == "completed":
        print(result.get("outputs", []))
        break
    if status in {"failed", "cancelled", "timeout"}:
        raise RuntimeError(result)
    if status not in {"created", "processing"}:
        raise RuntimeError(f"Unexpected status: {status}")
    time.sleep(2)

Gen4 Aleph API — Frequently asked questions

What is the Gen4 Aleph API?

Gen4 Aleph is a Runwayml model for video editing, exposed as a REST API on WaveSpeedAI. RunwayML Gen4 Aleph is a Video-to-Video model for editing, transforming, and generating video at $0.18 per second. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Gen4 Aleph API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/runwayml/runwayml-gen4-aleph.

How much does Gen4 Aleph cost per run?

Gen4 Aleph starts at $0.90 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Gen4 Aleph accept?

Key inputs: `prompt`, `video`, `aspect_ratio`, `reference_image`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/runwayml/runwayml-gen4-aleph.

How long does Gen4 Aleph take to generate?

Median end-to-end generation time on WaveSpeedAI is around 163 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.

Can I use Gen4 Aleph outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (Runwayml). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

Gen4 Aleph | AI Video Editing API | WaveSpeedAI