Seedream 5.0 Pro está no ar | Experimente no Gerador de Imagens →

Ray 2 Flash T2V

luma /

Luma Ray 2 Flash turns text into high-quality videos with flexible sizes and built-in prompt optimization for precise outputs. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

text-to-video
Entrada

Ocioso

$0.2por execução·~50 / $10

Próximo:

ExemplosVer todos

A time-lapse of a sunrise over a bustling city, 16-bit pixel art style. Tiny pixel cars move along the streets, and lights in the buildings turn off as the sun rises. Retro gaming aesthetic, vibrant pixelated colors. -camera tilt up slowly -motion 1

Dinner table set for two in a small backyard, hanging string lights, clinking glasses, slow zoom-out revealing surrounding plants and a fading sunset sky

A couple sitting on a rooftop at dusk, city skyline in the background, flickering candle on a table, soft wind rustling through their hair, quiet conversation

Teenagers gathered around a campfire in the woods, roasting marshmallows, fire crackling, shadows dancing on their faces, laughter and stories in the air

Young woman journaling by the window on a rainy afternoon, warm lighting, soft lo-fi music playing, steam rising from a tea mug, droplets racing down the glass

Elderly man reading a newspaper in a quiet neighborhood park, pigeons walking nearby, autumn leaves falling, soft wind rustling the trees

Roommates cleaning the apartment together, vacuum humming, sunlight pouring through the curtains, framed photos on the walls, casual laughter in the background

Candlelit dinner for two in a small apartment, soft jazz playing, wine glasses clinking, warm tones and intimate atmosphere

Weekend brunch in a backyard garden, pancakes, fruit platter, dog lying lazily nearby, sun filtering through leaves

A giant, translucent whale made of shimmering glass, gracefully swimming through a sky filled with fluffy, cotton-candy-colored clouds at sunset. Inside the whale, tiny bioluminescent jellyfish pulse with soft light. Epic scale, fantasy art, breathtaking, trending on ArtStation. -camera pan up -ar 16:9

Modelos relacionados

README

Luma Ray 2 Flash — Text-to-Video

Luma Ray 2 Flash is a fast and powerful text-to-video generation model from Luma AI that creates stunning videos from text descriptions. Generate high-quality 720p videos with smooth motion, creative styles, and cinematic quality — optimized for speed and efficiency.

Why It Stands Out

  • Fast generation: Flash variant optimized for quick video creation.
  • HD 720p output: Generate crisp 1280×720 videos with excellent clarity.
  • Prompt Enhancer: Built-in AI-powered prompt optimization for better results.
  • Creative control: Support for camera and motion parameters directly in prompts.
  • Flexible duration: Choose between 5 or 10 second video lengths.
  • Style versatility: Handles various styles from photorealistic to pixel art and animation.

Parameters

ParameterRequiredDescription
promptYesText description of the video you want to generate.
sizeNoOutput resolution (default: 1280×720).
durationNoVideo length: 5 or 10 seconds (default: 5).

How to Use

  1. Write a prompt describing the scene, action, and style you want. Use the Prompt Enhancer for AI-assisted optimization.
  2. Select size — choose the resolution that fits your needs.
  3. Set duration — choose 5 or 10 seconds.
  4. Click Run and wait for your video to generate.
  5. Preview and download the result.

Prompt Tips

You can include camera and motion controls directly in your prompt:

  • Camera movements: -camera tilt up slowly, -camera pan left, -camera zoom in
  • Motion intensity: -motion 1 (subtle) to -motion 5 (dynamic)

Example: "A sunset over mountains, cinematic style -camera tilt up slowly -motion 1"

Best Use Cases

  • Social Media Content — Create engaging video clips for TikTok, Reels, and Shorts.
  • Creative Animation — Generate stylized content like pixel art, anime, or retro aesthetics.
  • Marketing & Advertising — Produce promotional videos and ad creatives quickly.
  • Concept Visualization — Rapidly prototype video ideas before full production.
  • Game & App Content — Create trailers and promotional materials.

Pricing

DurationPrice
5 seconds$0.20
10 seconds$0.40

Pro Tips for Best Quality

  • Be detailed in your prompt — describe subject, action, environment, lighting, and style.
  • Use style keywords like "pixel art," "cinematic," "anime," or "retro gaming aesthetic."
  • Include camera controls for more dynamic, professional-looking results.
  • Adjust motion intensity based on your scene — use lower values for calm scenes, higher for action.
  • Start with 5-second videos to test concepts, then extend to 10 seconds for final versions.

Notes

  • Processing time varies based on duration and current queue load.
  • Please ensure your prompts comply with content guidelines.
Nota:Este site utiliza modelos de IA fornecidos por terceiros.

Ray 2 Flash T2v API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/luma/ray-2-flash-t2v 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 Ray 2 Flash T2v 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",
    "size": "1280*720",
    "duration": 5
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/luma/ray-2-flash-t2v" \
  -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/luma/ray-2-flash-t2v";
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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "size": "1280*720",
        "duration": 5
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${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",
    "size": "1280*720",
    "duration": 5
}

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/luma/ray-2-flash-t2v", 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)

Ray 2 Flash T2v API — Frequently asked questions

What is the Ray 2 Flash T2v API?

Ray 2 Flash T2v is a Luma model for video generation, exposed as a REST API on WaveSpeedAI. Luma Ray 2 Flash turns text into high-quality videos with flexible sizes and built-in prompt optimization for precise outputs. 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 Ray 2 Flash T2v 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/luma/luma-ray-2-flash-t2v.

How much does Ray 2 Flash T2v cost per run?

Ray 2 Flash T2v starts at $0.20 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 Ray 2 Flash T2v accept?

Key inputs: `prompt`, `duration`, `size`. 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/luma/luma-ray-2-flash-t2v.

How long does Ray 2 Flash T2v take to generate?

Median end-to-end generation time on WaveSpeedAI is around 150 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 Ray 2 Flash T2v outputs commercially?

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

Ray 2 Flash T2V | Powerful Text-to-Video API | WaveSpeedAI