Seedream 5.0 Pro 正式上線 | 在圖片生成器中體驗 →

Pixverse V4.5 T2V

pixverse /

Pixverse v4.5 turns text prompts into high-quality videos with multiple resolutions, aspect ratios, and motion modes. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

text-to-video
輸入

就緒

$0.25每次運行·~40 / $10

下一步:

示例查看全部

An astronaut floating weightlessly inside a space station, Earth visible outside the window, 4K cinematic shot

A lone motorcyclist rides through a neon-lit city at night, rain falling, slow motion, cinematic lighting

A ballerina performing on a dimly lit stage surrounded by fog, graceful movements, spotlight tracking

A child running through a field of sunflowers under a clear blue sky, handheld camera style, sunny lighting

A robot walking through a deserted cyberpunk city, glowing billboards flickering, camera panning slowly

A futuristic battle between drones in a dystopian wasteland, fast-paced, intense lighting, wide-angle view

A lion walking across the savanna with dust rising behind, golden hour, documentary-style lensing

A female spy in a black leather suit escaping through neon-lit alleyways at night, handheld camera, cinematic tension

A group of dancers performing hip-hop choreography in an urban plaza, flashing lights, multiple camera angles

A soldier crawling through a war-torn trench under fire, gritty textures, cinematic war footage look

相關模型

README

PixVerse V4.5 — Text-to-Video

PixVerse V4.5 Text-to-Video is a high-quality text-to-video generation model with support for resolutions up to Full HD 1080p. Generate detailed, cinematic videos from text descriptions with flexible aspect ratios and multiple resolution options.

Why It Stands Out

  • Up to 1080p Full HD: Generate crisp, high-resolution videos for professional use.
  • Multiple resolutions: Choose from 360p, 540p, 720p, or 1080p based on your needs.
  • Prompt Enhancer: Built-in AI-powered prompt optimization for better results.
  • Flexible aspect ratios: Wide range from 16:9 widescreen to 9:16 vertical.
  • Negative prompt support: Exclude unwanted elements for cleaner outputs.
  • Reproducibility: Use the seed parameter to recreate exact results.

Parameters

ParameterRequiredDescription
promptYesText description of the video you want to generate.
aspect_ratioYesOutput aspect ratio: 16:9, 4:3, 1:1, 3:4, 9:16.
resolutionYesOutput resolution: 360p, 540p, 720p, 1080p.
durationNoVideo length: 5 or 8 seconds (default: 5).
negative_promptNoElements to avoid in the output.
seedNoSet for reproducibility; leave empty for random.

Supported Resolutions

ResolutionBest For
360pQuick previews, drafts, low-bandwidth use
540pSocial media, balanced quality and speed
720pHD output, general professional use
1080pFull HD, premium quality, final delivery

Supported Aspect Ratios

Aspect RatioBest For
16:9YouTube, widescreen displays
4:3Classic format, presentations
1:1Instagram posts, social media squares
3:4Portrait photos, Pinterest
9:16TikTok, Instagram Stories, Reels

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 aspect ratio — choose the format that fits your platform.
  3. Select resolution — choose 360p for drafts, 1080p for premium output.
  4. Set duration — choose 5 or 8 seconds.
  5. Add a negative prompt (optional) — specify elements to exclude.
  6. Click Run and wait for your video to generate.
  7. Preview and download the result.

Best Use Cases

  • Cinematic Content — Generate 4K-style cinematic shots and scenes.
  • Social Media Content — Create platform-optimized videos for any channel.
  • Marketing & Advertising — Produce high-quality promotional videos.
  • Sci-Fi & Fantasy — Generate detailed, imaginative scenes.
  • Rapid Prototyping — Use lower resolutions for quick concept testing.

Pricing

Resolution5 seconds8 seconds
360p$0.25$0.50
540p$0.25$0.50
720p$0.35$0.70
1080p$0.70$1.40

Pro Tips for Best Quality

  • Be detailed in your prompt — describe subject, action, environment, lighting, and style.
  • Include quality keywords like "4K," "cinematic shot," or specific visual descriptions.
  • Use 360p or 540p for quick iterations, then generate final version at 1080p.
  • Use negative prompts to reduce artifacts like blur or distortion.
  • Match aspect ratio to your target platform before generating.

Notes

  • Processing time varies based on resolution, duration, and current queue load.
  • For faster generation at lower cost, consider PixVerse V4.5 Fast.
  • Please ensure your prompts comply with content guidelines.
提示:本網站部分功能由第三方 AI 模型提供支援。

Pixverse v4.5 T2v API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/pixverse/pixverse-v4.5-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 Pixverse v4.5 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",
    "aspect_ratio": "16:9",
    "resolution": "540p",
    "duration": 5
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/pixverse/pixverse-v4.5-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/pixverse/pixverse-v4.5-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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "aspect_ratio": "16:9",
        "resolution": "540p",
        "duration": 5
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${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",
    "aspect_ratio": "16:9",
    "resolution": "540p",
    "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/pixverse/pixverse-v4.5-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)

Pixverse v4.5 T2v API — Frequently asked questions

What is the Pixverse v4.5 T2v API?

Pixverse v4.5 T2v is a Pixverse model for video generation, exposed as a REST API on WaveSpeedAI. Pixverse v4.5 turns text prompts into high-quality videos with multiple resolutions, aspect ratios, and motion modes. 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 Pixverse v4.5 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/pixverse/pixverse-pixverse-v4.5-t2v.

How much does Pixverse v4.5 T2v cost per run?

Pixverse v4.5 T2v starts at $0.25 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 Pixverse v4.5 T2v accept?

Key inputs: `prompt`, `aspect_ratio`, `resolution`, `duration`, `seed`, `negative_prompt`. 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/pixverse/pixverse-pixverse-v4.5-t2v.

How long does Pixverse v4.5 T2v take to generate?

Median end-to-end generation time on WaveSpeedAI is around 64 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 Pixverse v4.5 T2v outputs commercially?

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

Pixverse V4.5 T2V | Powerful Text-to-Video API | WaveSpeedAI